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

    Neuronpedia

    INDEX
    Explanations

    text about personal aspirations, planning, or divine will.

    oai_token-act-pair · gemini-2.0-flash

    plans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enej
    -0.45
     wacht
    -0.44
    zad
    -0.44
    ędzy
    -0.43
    :]:
    -0.43
     exemplaires
    -0.41
     Eichen
    -0.41
    времен
    -0.40
     sektor
    -0.39
     préalable
    -0.39
    POSITIVE LOGITS
     plans
    2.45
     Plans
    2.20
    plans
    2.14
    Plans
    2.06
     plan
    2.02
     PLANS
    2.02
    plan
    1.84
     Plan
    1.81
    Plan
    1.73
     Pläne
    1.73
    Act Density 1.054%

    No Known Activations