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

    Neuronpedia

    INDEX
    Explanations

    Biological classifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FU
    -0.07
    ial
    -0.07
    Approved
    -0.06
     �
    -0.06
    ione
    -0.06
    썰
    -0.06
    rip
    -0.06
     situation
    -0.06
    стран
    -0.06
    ,is
    -0.06
    POSITIVE LOGITS
     дома
    0.08
    .adapters
    0.08
     Capcom
    0.07
    أشخاص
    0.07
     necklace
    0.07
    ぽ
    0.07
     hectares
    0.07
    _decrypt
    0.07
    .Row
    0.07
    트
    0.07
    Act Density 0.007%

    No Known Activations