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

    Neuronpedia

    INDEX
    Explanations

    computer devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _clr
    -0.08
     Brenda
    -0.07
    ergency
    -0.06
    emsp
    -0.06
    .ToString
    -0.06
     Duterte
    -0.06
     Filipino
    -0.06
    heatmap
    -0.06
     мов
    -0.06
    
    -0.06
    POSITIVE LOGITS
     copying
    0.06
    cription
    0.06
    音
    0.06
     hues
    0.06
     ambiguous
    0.06
     Constraints
    0.06
    (parameter
    0.06
    olucion
    0.06
    ogenerated
    0.06
     intimidation
    0.06
    Act Density 0.091%

    No Known Activations