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

    Neuronpedia

    INDEX
    Explanations

    basal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interoper
    -0.08
    VOID
    -0.08
     minutos
    -0.07
     onc
    -0.07
    ترجم
    -0.07
    缘
    -0.07
    =bool
    -0.07
     hatırl
    -0.07
    大军
    -0.07
     specificity
    -0.07
    POSITIVE LOGITS
    	output
    0.08
     같이
    0.07
    Rejected
    0.07
    Ca
    0.07
     pam
    0.07
    利用
    0.06
    ulado
    0.06
     closed
    0.06
     Ca
    0.06
    风扇
    0.06
    Act Density 0.002%

    No Known Activations