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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    袤
    -0.07
     remind
    -0.07
    kind
    -0.07
     reminds
    -0.07
    SELL
    -0.07
     kind
    -0.07
     szy
    -0.07
    紧紧
    -0.07
    身心
    -0.07
    חינ
    -0.07
    POSITIVE LOGITS
    Alarm
    0.07
    _secondary
    0.07
    documentation
    0.07
    عارض
    0.06
    -placeholder
    0.06
    Possible
    0.06
    0.06
    argest
    0.06
    "What
    0.06
     interrogation
    0.06
    Act Density 0.012%

    No Known Activations