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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Proceed
    -0.07
    illustr
    -0.07
    +_
    -0.07
    ancial
    -0.07
     Krishna
    -0.07
     indebted
    -0.07
    🐋
    -0.07
     Illustrated
    -0.06
    Outlined
    -0.06
    blem
    -0.06
    POSITIVE LOGITS
    直升
    0.07
     xlim
    0.07
     vent
    0.07
    IntegerField
    0.07
     Colon
    0.07
    альное
    0.06
    Fly
    0.06
     אחרות
    0.06
    แรก
    0.06
     operand
    0.06
    Act Density 0.001%

    No Known Activations