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

    Neuronpedia

    INDEX
    Explanations

    public events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Save
    -0.08
    gain
    -0.07
    ception
    -0.06
     ascent
    -0.06
    Yep
    -0.06
     dị
    -0.06
    Peak
    -0.06
    face
    -0.06
    ，但
    -0.06
    			↵↵
    -0.06
    POSITIVE LOGITS
     fv
    0.07
    HasColumnName
    0.06
     допом
    0.06
    ington
    0.06
     درآمد
    0.06
    .linkedin
    0.06
     Verm
    0.06
     aşam
    0.06
    berman
    0.06
    ание
    0.06
    Act Density 0.138%

    No Known Activations