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

    Neuronpedia

    INDEX
    Explanations

    consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _constraint
    -0.07
    _numbers
    -0.07
     Threshold
    -0.07
     heavy
    -0.06
     ICC
    -0.06
     ethers
    -0.06
    _socket
    -0.06
     along
    -0.06
     casts
    -0.06
    .Blocks
    -0.06
    POSITIVE LOGITS
    ấ
    0.08
     Morocco
    0.07
    ()='
    0.06
     quale
    0.06
    ��
    0.06
    retorno
    0.06
     COR
    0.06
    ΑΓ
    0.06
     vivastreet
    0.06
     récup
    0.06
    Act Density 0.015%

    No Known Activations