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

    Neuronpedia

    INDEX
    Explanations

    Code permissions/access control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    תם
    -0.07
    den
    -0.06
    端正
    -0.06
    ningen
    -0.06
    atsby
    -0.06
     Neo
    -0.06
    Ark
    -0.06
     Nuggets
    -0.06
    _FETCH
    -0.06
     America
    -0.06
    POSITIVE LOGITS
    _local
    0.08
    肉
    0.07
    _Error
    0.07
     aque
    0.07
    โคร
    0.07
    -income
    0.07
    .server
    0.07
     Shares
    0.06
     Coffee
    0.06
    reur
    0.06
    Act Density 0.008%

    No Known Activations