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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auss
    -0.06
    /sn
    -0.06
    .must
    -0.06
    _ABC
    -0.06
    arte
    -0.06
     drilled
    -0.06
     userRepository
    -0.06
     Blue
    -0.06
     KP
    -0.06
    ]._
    -0.06
    POSITIVE LOGITS
    illusion
    0.06
    apeutic
    0.06
    selectors
    0.06
     浙江
    0.06
    ajar
    0.06
    slick
    0.06
    �
    0.06
    ég
    0.06
    κού
    0.06
    BeenCalled
    0.06
    Act Density 0.019%

    No Known Activations