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

    Neuronpedia

    INDEX
    Explanations

    Conversational language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |null
    -0.08
     그러
    -0.07
    Democratic
    -0.07
     mà
    -0.07
    기업
    -0.07
    ,…↵↵
    -0.07
     }],↵
    -0.06
    entarios
    -0.06
     уж
    -0.06
     Completely
    -0.06
    POSITIVE LOGITS
     classifier
    0.07
     �
    0.07
    IFICATIONS
    0.06
     dou
    0.06
    Unified
    0.06
     unpl
    0.06
    _filled
    0.06
     filled
    0.06
    /services
    0.06
     sulfate
    0.06
    Act Density 0.051%

    No Known Activations