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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    麥
    -0.08
     Juliet
    -0.07
     Helen
    -0.07
    �
    -0.07
    ART
    -0.07
     lace
    -0.07
    FP
    -0.07
     historic
    -0.07
     rodents
    -0.07
    .getBlock
    -0.07
    POSITIVE LOGITS
     Detailed
    0.08
    meth
    0.07
    似
    0.07
    结构调整
    0.07
    unner
    0.07
    PARTMENT
    0.07
    0.07
    Impossible
    0.07
     resultCode
    0.07
    defaults
    0.06
    Act Density 0.293%

    No Known Activations