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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    f
    -0.08
    _ptr
    -0.07
    proposal
    -0.07
    .hour
    -0.06
    fre
    -0.06
    .Event
    -0.06
     laughed
    -0.06
    prefer
    -0.06
     рождения
    -0.06
    Client
    -0.06
    POSITIVE LOGITS
    .*;
↵
↵
    0.07
    _GP
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     preset
    0.06
    .rcParams
    0.06
     Fonts
    0.06
     capacidad
    0.06
    };↵↵↵↵
    0.06
    acion
    0.06
    ,､
    0.06
    Act Density 0.010%

    No Known Activations