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

    Neuronpedia

    INDEX
    Explanations

    sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pond
    -0.07
    мещ
    -0.07
    rides
    -0.07
    thead
    -0.06
     reviewed
    -0.06
    _HORIZONTAL
    -0.06
     jméno
    -0.06
    eat
    -0.06
     �
    -0.06
    盗
    -0.06
    POSITIVE LOGITS
    .num
    0.06
     vra
    0.06
     IDb
    0.06
    .LAZY
    0.06
     osg
    0.06
     tablespoon
    0.06
     Json
    0.06
     constituents
    0.06
    _CREATED
    0.06
     Sala
    0.06
    Act Density 0.000%

    No Known Activations