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

    Neuronpedia

    INDEX
    Explanations

    signs or indications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     初
    -0.07
    _COLLECTION
    -0.06
     Jenny
    -0.06
     von
    -0.06
     چون
    -0.06
     famously
    -0.06
     cursos
    -0.06
     Nó
    -0.06
     jerk
    -0.06
     styling
    -0.06
    POSITIVE LOGITS
     indicative
    0.07
     значит
    0.07
    跌
    0.07
    cheiden
    0.06
     non
    0.06
    chein
    0.06
    uje
    0.06
    ulty
    0.06
     handful
    0.06
    ��
    0.06
    Act Density 0.041%

    No Known Activations