Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to research methodologies and experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text fragments before commas

    np_acts-logits-general · gemini-2.0-flash

    study descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.65
    protoimpl
    -0.58
     vå
    -0.52
    AddTagHelper
    -0.52
     lenker
    -0.52
    ResponseWriter
    -0.52
    теризу
    -0.50
     debout
    -0.50
    AndEndTag
    -0.50
     lumineuse
    -0.49
    POSITIVE LOGITS
     jsPsych
    0.66
    帖最后由
    0.58
    })}$
    0.56
     mistakes
    0.55
     efficiencies
    0.54
    istoitu
    0.52
     lessons
    0.51
     errors
    0.51
    moires
    0.50
    }}/>
    0.50
    Act Density 1.521%

    No Known Activations