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

    Neuronpedia

    INDEX
    Explanations

    sudden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     расход
    -0.07
     رو
    -0.07
     atual
    -0.07
     vitro
    -0.07
     demol
    -0.07
     archivo
    -0.07
    各个方面
    -0.07
    ar
    -0.07
    resize
    -0.07
    opsis
    -0.07
    POSITIVE LOGITS
     Smy
    0.09
     عدم
    0.08
    衿
    0.07
    ximity
    0.07
    ipment
    0.07
     DJ
    0.07
    _picture
    0.07
     Knights
    0.07
    _emails
    0.07
     medals
    0.07
    Act Density 0.007%

    No Known Activations