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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("[%
    -0.08
    sd
    -0.07
     Tf
    -0.07
     Zus
    -0.07
     BST
    -0.06
    polation
    -0.06
    anja
    -0.06
    ISIS
    -0.06
    isor
    -0.06
    “(
    -0.06
    POSITIVE LOGITS
    _redirected
    0.06
     attaching
    0.06
     brilliant
    0.06
    food
    0.06
    Hair
    0.06
     techniques
    0.06
     basic
    0.06
    Charlotte
    0.06
    _mul
    0.06
     prognosis
    0.06
    Act Density 0.000%

    No Known Activations