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

    Neuronpedia

    INDEX
    Explanations

    concentrations and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woo
    -0.07
    916
    -0.07
     Tran
    -0.07
    824
    -0.07
    oriented
    -0.07
    .D
    -0.07
     clave
    -0.06
    fir
    -0.06
    tran
    -0.06
     Des
    -0.06
    POSITIVE LOGITS
     />)↵
    0.07
    [iVar
    0.06
    SocketAddress
    0.06
     VERIFY
    0.06
     interoper
    0.06
     Amateur
    0.06
     onder
    0.06
    spell
    0.06
     ngành
    0.06
    _softmax
    0.06
    Act Density 0.007%

    No Known Activations