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

    Neuronpedia

    INDEX
    Explanations

    statements outlining the objectives of various studies or projects

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

    objective of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    geslacht
    -0.49
    adona
    -0.48
    wies
    -0.48
    hacks
    -0.47
    isat
    -0.45
    endix
    -0.45
     Xm
    -0.45
    pete
    -0.45
     calculators
    -0.45
    empl
    -0.44
    POSITIVE LOGITS
     objective
    0.93
     aim
    0.89
     objectif
    0.88
     objetivo
    0.88
     objectives
    0.87
     Tujuan
    0.85
    objectif
    0.85
     objectifs
    0.84
    Tujuan
    0.83
    objetivo
    0.82
    Act Density 0.043%

    No Known Activations