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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acci
    -0.06
    ificant
    -0.06
    apt
    -0.06
    207
    -0.06
    一度
    -0.06
    bringing
    -0.06
    Trust
    -0.06
    >i
    -0.06
     Kar
    -0.06
    Immutable
    -0.06
    POSITIVE LOGITS
     Dumpster
    0.08
     Yun
    0.07
     wer
    0.07
     Frm
    0.07
    .
↵
    0.07
     маз
    0.07
     Ryu
    0.06
    _DEPRECATED
    0.06
     Mob
    0.06
     направ
    0.06
    Act Density 0.014%

    No Known Activations