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

    Neuronpedia

    INDEX
    Explanations

    the,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ist
    -0.07
     cheese
    -0.07
     sunday
    -0.06
     damit
    -0.06
    _bounds
    -0.06
     Kenny
    -0.06
    发送
    -0.06
     теперь
    -0.06
    /top
    -0.06
    -from
    -0.06
    POSITIVE LOGITS
     وا
    0.07
     phường
    0.06
     maxLength
    0.06
    flu
    0.06
     CString
    0.06
    慧
    0.06
    ngör
    0.06
    angular
    0.06
    �다
    0.06
     TABLE
    0.06
    Act Density 0.042%

    No Known Activations