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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cou
    -0.07
    gif
    -0.06
     fem
    -0.06
    ised
    -0.06
    iyas
    -0.06
    YT
    -0.06
    ipel
    -0.06
     �
    -0.06
    ランド
    -0.06
    uj
    -0.06
    POSITIVE LOGITS
     Definition
    0.07
    .XRLabel
    0.07
    sembles
    0.07
     OutputStream
    0.07
    ReadStream
    0.07
     ASF
    0.07
    产生
    0.07
     punish
    0.06
    .window
    0.06
     uygulama
    0.06
    Act Density 0.000%

    No Known Activations