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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tune
    -0.07
    learner
    -0.07
    唯
    -0.07
    MainWindow
    -0.06
     tunes
    -0.06
    Direct
    -0.06
    Tiny
    -0.06
     szy
    -0.06
     Regina
    -0.06
     Charg
    -0.06
    POSITIVE LOGITS
     things
    0.07
    _DECREF
    0.07
     deletion
    0.06
    (instr
    0.06
    pres
    0.06
    (owner
    0.06
    mongodb
    0.06
     barriers
    0.06
    bsd
    0.06
     sonra
    0.06
    Act Density 0.052%

    No Known Activations