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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pers
    -0.07
    (Guid
    -0.07
     obligation
    -0.07
     doğrult
    -0.06
    "While
    -0.06
     blot
    -0.06
     nostalgia
    -0.06
     fil
    -0.06
     intervals
    -0.06
    教授
    -0.06
    POSITIVE LOGITS
     massasje
    0.07
    인데
    0.06
    .exceptions
    0.06
    Active
    0.06
    <U
    0.06
    _vp
    0.06
    );
↵
↵
↵
    0.06
    }%
    0.06
    Unsafe
    0.06
    _KERNEL
    0.06
    Act Density 0.019%

    No Known Activations