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

    Neuronpedia

    INDEX
    Explanations

    technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accuracy
    -0.06
    <>(
    -0.06
     satisfies
    -0.06
    asurable
    -0.06
     Cummings
    -0.06
     Validation
    -0.06
     Knife
    -0.06
    _accuracy
    -0.06
     interview
    -0.06
     Geb
    -0.06
    POSITIVE LOGITS
     bacter
    0.07
     고려
    0.06
    交易
    0.06
    /form
    0.06
    OAD
    0.06
    remainder
    0.06
    flamm
    0.06
     �
    0.06
     路
    0.06
     giàu
    0.06
    Act Density 0.000%

    No Known Activations