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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diagnose
    -0.07
     synonymous
    -0.07
     diagnosis
    -0.07
    ATUS
    -0.07
    acute
    -0.06
    NSE
    -0.06
    董事
    -0.06
    辒
    -0.06
     Mood
    -0.06
    LAY
    -0.06
    POSITIVE LOGITS
    բ
    0.07
    مثل
    0.07
    𝓱
    0.06
    溴
    0.06
     אר
    0.06
    .UserID
    0.06
     defining
    0.06
    Conn
    0.06
     handlers
    0.06
     Handles
    0.06
    Act Density 0.021%

    No Known Activations