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

    Neuronpedia

    INDEX
    Explanations

    Code/URL snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    727
    -0.06
    ture
    -0.06
    odule
    -0.06
     cl
    -0.06
     Malcolm
    -0.06
     rejoice
    -0.06
    /memory
    -0.06
    isable
    -0.06
    _use
    -0.06
    ().__
    -0.06
    POSITIVE LOGITS
     khung
    0.07
    Several
    0.07
     önce
    0.06
    _Address
    0.06
     Obtain
    0.06
    lisi
    0.06
     zeigt
    0.06
    编
    0.06
     backbone
    0.06
    ,proto
    0.06
    Act Density 0.000%

    No Known Activations