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

    Neuronpedia

    INDEX
    Explanations

    discussed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     witness
    -0.07
    iaux
    -0.06
    =$(
    -0.06
    APA
    -0.06
    sei
    -0.06
     shin
    -0.06
     iVar
    -0.06
    hdl
    -0.06
     rotten
    -0.06
    iris
    -0.06
    POSITIVE LOGITS
     Microsoft
    0.08
    Microsoft
    0.07
     microwave
    0.06
    鸡
    0.06
    tot
    0.06
    icture
    0.06
     النظام
    0.06
    dic
    0.06
     germ
    0.06
    ovaných
    0.06
    Act Density 0.000%

    No Known Activations