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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abinet
    -0.06
    "[
    -0.06
     е
    -0.06
    Η
    -0.06
     staged
    -0.06
    ุส
    -0.06
     toda
    -0.06
     mh
    -0.06
     залеж
    -0.06
    _ACTIVITY
    -0.05
    POSITIVE LOGITS
    .light
    0.08
    adin
    0.07
    운동
    0.07
    /preferences
    0.07
    _month
    0.07
     acknowledged
    0.07
    Decl
    0.06
    олуч
    0.06
    maf
    0.06
    .days
    0.06
    Act Density 0.000%

    No Known Activations