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

    Neuronpedia

    INDEX
    Explanations

    Apache License 2.0 headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polynomial
    -0.07
    وقف
    -0.06
    -watch
    -0.06
    urgence
    -0.06
    _regularizer
    -0.06
    ระบ
    -0.06
     astronomy
    -0.06
     @"";↵
    -0.06
     fre
    -0.06
     желез
    -0.06
    POSITIVE LOGITS
    _weak
    0.06
    uct
    0.06
    _manage
    0.06
    Verb
    0.06
     Square
    0.06
    leep
    0.06
     stip
    0.06
     happens
    0.05
     sofa
    0.05
     bearings
    0.05
    Act Density 0.001%

    No Known Activations