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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Apr
    -0.07
    ыв
    -0.06
    Thursday
    -0.06
    اى
    -0.06
     atheist
    -0.06
     gtk
    -0.06
    -star
    -0.06
    รรค
    -0.06
    CCC
    -0.06
     suggests
    -0.06
    POSITIVE LOGITS
    osite
    0.07
     goof
    0.06
    Falsy
    0.06
     اللغة
    0.06
    ,__
    0.06
    (contents
    0.06
    _VALIDATE
    0.06
    .autoconfigure
    0.06
    _act
    0.06
     nihil
    0.06
    Act Density 0.039%

    No Known Activations