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

    Neuronpedia

    INDEX
    Explanations

    Android code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lowes
    -0.07
     liked
    -0.06
    会
    -0.06
    while
    -0.06
     waste
    -0.06
     classroom
    -0.06
    ья
    -0.06
     गई
    -0.06
    umni
    -0.06
    addListener
    -0.06
    POSITIVE LOGITS
    řez
    0.06
     ایست
    0.06
    .endswith
    0.06
    Но
    0.06
    AFE
    0.06
    URED
    0.06
     бли
    0.06
     Parti
    0.06
    _fa
    0.06
     pave
    0.06
    Act Density 0.011%

    No Known Activations