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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lbl
    -0.08
    (entries
    -0.07
    (tmp
    -0.06
     imágenes
    -0.06
     Roads
    -0.06
    _Update
    -0.06
    уття
    -0.06
     Swamp
    -0.06
     propri
    -0.06
     cores
    -0.06
    POSITIVE LOGITS
    :P
    0.08
     조금
    0.07
    �
    0.06
     HM
    0.06
    [,
    0.06
    sdale
    0.06
     gradient
    0.06
     Pearce
    0.06
    аю
    0.06
    εχ
    0.06
    Act Density 0.011%

    No Known Activations