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

    Neuronpedia

    INDEX
    Explanations

    discussions around making choices and ensuring satisfactory outcomes

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

    Text after specific capitalized words

    np_acts-logits-general · gemini-2.0-flash

    contextual qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.61
    Lähteet
    -0.59
     للمعارف
    -0.56
    issage
    -0.54
     Roskov
    -0.53
     său
    -0.52
    WriteAttribute
    -0.50
     kaarangay
    -0.50
     rând
    -0.49
    ↵↵↵
    -0.48
    POSITIVE LOGITS
    вЂ
    0.60
     dudes
    0.57
    bootstrapcdn
    0.57
     posses
    0.54
    ulence
    0.54
    ]^
    0.54
    €”
    0.53
    RenderAtEndOf
    0.53
     UNITED
    0.53
     babes
    0.52
    Act Density 0.078%

    No Known Activations