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

    Neuronpedia

    INDEX
    Explanations

    terms related to preliminary research findings

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

    preliminary results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.42
     millions
    -0.36
     autant
    -0.34
    UnifiedTopology
    -0.34
     AssemblyCompany
    -0.34
     recargable
    -0.32
     Castle
    -0.32
     Erwachsene
    -0.31
    forhold
    -0.31
     pierna
    -0.30
    POSITIVE LOGITS
    liminary
    0.90
     preliminary
    0.84
     rudimentary
    0.84
    初步
    0.81
     Preliminary
    0.79
    tagHelperRunner
    0.77
    Preliminary
    0.75
     prelimin
    0.74
    tvguidetime
    0.69
     PRELIM
    0.66
    Act Density 0.205%

    No Known Activations