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
    (Console
    -0.07
    apgolly
    -0.07
     �
    -0.06
    appiness
    -0.06
    /cop
    -0.06
    pressive
    -0.06
    _sequences
    -0.06
    '],$
    -0.06
     tangent
    -0.06
     CDs
    -0.06
    POSITIVE LOGITS
    ém
    0.07
    ौर
    0.07
     petition
    0.07
     hij
    0.06
    бра
    0.06
    Jobs
    0.06
     тяж
    0.06
     upset
    0.06
    ∏
    0.06
    WebSocket
    0.06
    Act Density 0.004%

    No Known Activations