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

    Neuronpedia

    INDEX
    Explanations

    journal publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emergencies
    -0.08
    ריש
    -0.07
    ugged
    -0.07
    (Thread
    -0.07
     appro
    -0.06
    .slim
    -0.06
     special
    -0.06
    重启
    -0.06
    “These
    -0.06
     KeyValue
    -0.06
    POSITIVE LOGITS
    asset
    0.08
    thrown
    0.07
    Painter
    0.06
    Holder
    0.06
    晋
    0.06
    .Media
    0.06
    _rnn
    0.06
    Capture
    0.06
    hunter
    0.06
    Candidates
    0.06
    Act Density 0.018%

    No Known Activations