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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exh
    -0.07
    gs
    -0.07
    zes
    -0.06
     RECE
    -0.06
     fp
    -0.06
    HW
    -0.06
     χρή
    -0.06
    tram
    -0.06
    _RC
    -0.06
    ıp
    -0.06
    POSITIVE LOGITS
     Emails
    0.07
     tamam
    0.07
    Gallery
    0.07
    Beauty
    0.07
     Dangerous
    0.06
    responsive
    0.06
    aic
    0.06
    _typeDefinitionSize
    0.06
    UGIN
    0.06
     nearby
    0.06
    Act Density 0.176%

    No Known Activations