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

    Neuronpedia

    INDEX
    Explanations

    mongo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unicip
    -0.08
     fluffy
    -0.08
    fft
    -0.08
    .before
    -0.07
    (custom
    -0.07
     Willis
    -0.07
     certs
    -0.07
    UMMY
    -0.07
    大厦
    -0.07
     Regiment
    -0.07
    POSITIVE LOGITS
    ภ
    0.07
     with
    0.07
    ork
    0.07
    他の
    0.07
    0.07
    มอบ
    0.07
    .goBack
    0.06
    𝘰
    0.06
    菏泽
    0.06
    精准扶贫
    0.06
    Act Density 0.004%

    No Known Activations