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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nto
    -0.06
     Cock
    -0.06
    /socket
    -0.06
    .core
    -0.06
    或者
    -0.06
    νος
    -0.05
    ível
    -0.05
    .dumps
    -0.05
    another
    -0.05
    fulWidget
    -0.05
    POSITIVE LOGITS
    ват
    0.07
    ERA
    0.07
    IRA
    0.06
     prevent
    0.06
     베스트
    0.06
     uncont
    0.06
     Prevent
    0.06
     ولم
    0.06
    lut
    0.06
    (ConfigurationManager
    0.06
    Act Density 0.001%

    No Known Activations