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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JNIEnv
    -0.07
    Trong
    -0.06
    нож
    -0.06
    tid
    -0.06
    Programming
    -0.06
    bate
    -0.06
    uyến
    -0.06
    rysler
    -0.06
    �
    -0.06
     сах
    -0.06
    POSITIVE LOGITS
     朝
    0.07
    _DEPRECATED
    0.07
     adore
    0.06
    Db
    0.06
     editable
    0.06
    のみ
    0.06
     Requirement
    0.06
    ,array
    0.06
    ISED
    0.06
     оброб
    0.06
    Act Density 0.003%

    No Known Activations