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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("@
    -0.07
    Positive
    -0.07
    "Some
    -0.06
    vol
    -0.06
    .Sc
    -0.06
    ATES
    -0.06
    profits
    -0.06
    ίου
    -0.06
    "For
    -0.06
    _PUS
    -0.06
    POSITIVE LOGITS
     velik
    0.07
    unfinished
    0.07
    -left
    0.07
    ظام
    0.06
    .calculate
    0.06
     się
    0.06
    体系
    0.06
     tener
    0.06
     checkboxes
    0.06
     militia
    0.06
    Act Density 0.001%

    No Known Activations