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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oriented
    -0.08
    燹
    -0.07
    淆
    -0.07
    ipated
    -0.07
    معرف
    -0.07
    黻
    -0.07
    腹
    -0.07
    第一步
    -0.07
    ۩
    -0.07
     Kaplan
    -0.06
    POSITIVE LOGITS
    .camel
    0.08
    (^)(
    0.08
    _Pods
    0.07
    .springframework
    0.07
     autorelease
    0.07
    (instr
    0.07
     טוב
    0.07
    ()};↵
    0.07
     GLES
    0.07
    佁
    0.06
    Act Density 0.032%

    No Known Activations