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

    Neuronpedia

    INDEX
    Explanations

    early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aud
    -0.07
    /I
    -0.07
     advocate
    -0.07
    Cisco
    -0.06
    _dur
    -0.06
     rtl
    -0.06
     fortress
    -0.06
     Keyword
    -0.06
    cheduling
    -0.06
     CAN
    -0.06
    POSITIVE LOGITS
     MAG
    0.06
     Horizon
    0.06
    (Result
    0.06
    乱
    0.06
     Examiner
    0.06
     کیل
    0.06
     Judith
    0.06
    ΙΚΟ
    0.06
    -gay
    0.06
     circa
    0.06
    Act Density 0.000%

    No Known Activations