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

    Neuronpedia

    INDEX
    Explanations

    chemicals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Catalog
    -0.08
     longitud
    -0.08
    ū
    -0.07
    世界各国
    -0.07
    graph
    -0.07
    粱
    -0.07
    紧扣
    -0.07
    归纳
    -0.07
    ombres
    -0.07
    behavior
    -0.07
    POSITIVE LOGITS
    浠
    0.07
    (js
    0.07
     relentlessly
    0.07
     Louisville
    0.07
    (timeout
    0.07
    (bt
    0.07
     campaigning
    0.07
     credentials
    0.06
    .manual
    0.06
    ,H
    0.06
    Act Density 0.011%

    No Known Activations