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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Persistence
    -0.07
     built
    -0.07
    =P
    -0.07
    uilt
    -0.06
     espera
    -0.06
    092
    -0.06
     solvent
    -0.06
    >M
    -0.06
    ΟΚ
    -0.06
    especially
    -0.06
    POSITIVE LOGITS
    Modifiers
    0.07
    (ms
    0.06
     actividades
    0.06
    ;margin
    0.06
    划
    0.06
     полож
    0.06
    画像
    0.06
     расход
    0.06
     intéress
    0.06
    _criteria
    0.06
    Act Density 0.020%

    No Known Activations