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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wyświetl
    -0.07
    .tokenize
    -0.07
    夏天
    -0.07
     objectAtIndex
    -0.07
    :semicolon
    -0.07
    翈
    -0.07
     weighs
    -0.07
    ╇
    -0.07
    aleur
    -0.07
    	vec
    -0.07
    POSITIVE LOGITS
     BACK
    0.08
     hadn
    0.07
     Peg
    0.07
     outbound
    0.07
     Dortmund
    0.07
     Walnut
    0.07
    Apart
    0.07
     narcotics
    0.07
    旯
    0.07
    沧
    0.06
    Act Density 0.002%

    No Known Activations