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

    Neuronpedia

    INDEX
    Explanations

    Individual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    옯
    -0.07
     אחרונות
    -0.07
    .',
↵
    -0.06
     char
    -0.06
    ＆
    -0.06
     misunderstand
    -0.06
    原子
    -0.06
    ァ
    -0.06
    �
    -0.06
    캥
    -0.06
    POSITIVE LOGITS
    Trace
    0.08
     Harness
    0.07
    vic
    0.07
    tica
    0.07
    capability
    0.07
    roy
    0.07
    �
    0.07
    ester
    0.07
    urnal
    0.07
    (optional
    0.07
    Act Density 0.030%

    No Known Activations