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

    Neuronpedia

    INDEX
    Explanations

    anes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...">↵
    -0.07
     araç
    -0.07
     б
    -0.07
    .xy
    -0.06
    foto
    -0.06
     สพ
    -0.06
    爷
    -0.06
     speculate
    -0.06
     реж
    -0.06
    serir
    -0.06
    POSITIVE LOGITS
    ches
    0.06
    EndElement
    0.06
    LIK
    0.06
    statuses
    0.06
     Prostitutas
    0.06
    okes
    0.06
     lado
    0.06
     SDLK
    0.06
     Thing
    0.06
    transforms
    0.06
    Act Density 0.236%

    No Known Activations