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

    Neuronpedia

    INDEX
    Explanations

    cellular networks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Since
    -0.07
    orta
    -0.06
     Since
    -0.06
    inations
    -0.06
    _chain
    -0.06
     surgeon
    -0.06
     rằng
    -0.06
    _QUERY
    -0.06
    Chain
    -0.06
     torso
    -0.06
    POSITIVE LOGITS
    AppBundle
    0.07
    .RegisterType
    0.07
     REC
    0.06
     Аз
    0.06
     exempl
    0.06
    ([\
    0.06
     Jeremy
    0.06
     inconsistencies
    0.06
    ￣￣
    0.06
     ＞
    0.06
    Act Density 0.031%

    No Known Activations