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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Object
    -0.07
     прор
    -0.06
     jeep
    -0.06
     diagnostics
    -0.06
    ��
    -0.06
     FLT
    -0.06
    .,
    -0.06
     Torah
    -0.06
     Bak
    -0.06
     objetos
    -0.06
    POSITIVE LOGITS
    Linux
    0.07
    數
    0.07
    erver
    0.06
     documented
    0.06
     数
    0.06
     COVID
    0.06
    ότε
    0.06
    .ast
    0.06
    screens
    0.06
     aware
    0.06
    Act Density 0.020%

    No Known Activations