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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुर
    -0.07
     August
    -0.06
    _gap
    -0.06
    Server
    -0.06
    putc
    -0.06
     fascinating
    -0.06
    -new
    -0.06
    encrypted
    -0.06
     franc
    -0.06
    gear
    -0.06
    POSITIVE LOGITS
    祝
    0.07
    =pos
    0.07
     FileInputStream
    0.06
     Độ
    0.06
    既然
    0.06
     mol
    0.06
    bracht
    0.06
     říj
    0.06
     коштів
    0.06
    dsn
    0.06
    Act Density 0.122%

    No Known Activations