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

    Neuronpedia

    INDEX
    Explanations

    copyright protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PT
    -0.08
    !'
    -0.07
     Institute
    -0.07
     área
    -0.07
    _aug
    -0.07
    掳
    -0.07
     landmark
    -0.07
     AD
    -0.07
     eliminar
    -0.07
     voter
    -0.07
    POSITIVE LOGITS
    rott
    0.07
    conj
    0.07
    䣘
    0.07
    铭记
    0.07
    zähl
    0.07
    _connection
    0.07
    下称
    0.07
    גלגל
    0.07
    Rh
    0.07
    alties
    0.07
    Act Density 0.011%

    No Known Activations