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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.07
     purity
    -0.06
    Rad
    -0.06
     newList
    -0.06
    ông
    -0.06
    .Password
    -0.06
     oxide
    -0.06
     wore
    -0.06
    ㆍ
    -0.06
     correl
    -0.06
    POSITIVE LOGITS
    zej
    0.07
    ratings
    0.06
    атков
    0.06
    lagen
    0.06
     librarian
    0.06
    legt
    0.06
    ukt
    0.06
    ंट
    0.06
     مطرح
    0.06
    記
    0.06
    Act Density 0.000%

    No Known Activations