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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     camps
    -0.07
     paralyzed
    -0.07
     Crazy
    -0.07
    *y
    -0.07
     CWE
    -0.07
     pulumi
    -0.06
     vital
    -0.06
    _total
    -0.06
    	strcpy
    -0.06
    CHandle
    -0.06
    POSITIVE LOGITS
    Activate
    0.06
     инт
    0.06
     divisive
    0.06
     tribe
    0.06
    ampiyon
    0.06
    çok
    0.06
    áhnout
    0.06
     منطقه
    0.06
    Compilation
    0.06
     {"
    0.06
    Act Density 0.045%

    No Known Activations