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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    康
    -0.07
     surtout
    -0.07
    -controls
    -0.07
    Recording
    -0.07
    一年
    -0.07
    Frequency
    -0.07
    hibition
    -0.07
     squirt
    -0.07
    dbus
    -0.06
     spring
    -0.06
    POSITIVE LOGITS
    ิญ
    0.07
     červ
    0.06
    .inflate
    0.06
    _else
    0.06
    alsa
    0.06
     qualification
    0.06
     evidence
    0.06
    ющ
    0.06
    aterno
    0.06
    amon
    0.06
    Act Density 0.001%

    No Known Activations