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

    Neuronpedia

    INDEX
    Explanations

    Nathan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いる
    -0.07
    private
    -0.07
     Dim
    -0.07
     restarting
    -0.06
     Sodium
    -0.06
     abstract
    -0.06
     Generic
    -0.06
    (Value
    -0.06
     kernel
    -0.06
    (identifier
    -0.06
    POSITIVE LOGITS
     Nathan
    0.08
    enen
    0.07
    반기
    0.07
     StObject
    0.07
    ined
    0.06
    viol
    0.06
    سد
    0.06
     ben
    0.06
    athan
    0.06
    STANCE
    0.06
    Act Density 0.001%

    No Known Activations