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

    Neuronpedia

    INDEX
    Explanations

    internet forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pagination
    -0.07
    _reward
    -0.07
    e
    -0.06
     соот
    -0.06
    .endsWith
    -0.06
    ist
    -0.06
    curacy
    -0.06
     overwhelmingly
    -0.06
    be
    -0.06
     Tai
    -0.06
    POSITIVE LOGITS
     NSURL
    0.07
    !"
    0.07
    IDEO
    0.06
    getClass
    0.06
    xc
    0.06
    Instr
    0.06
     SUM
    0.06
    減
    0.06
     Durham
    0.06
     subsystem
    0.06
    Act Density 0.074%

    No Known Activations