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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subscriber
    -0.07
    خوان
    -0.07
    ए
    -0.07
    iphertext
    -0.07
    erial
    -0.06
    ίκ
    -0.06
    idae
    -0.06
    udoku
    -0.06
    орож
    -0.06
     theolog
    -0.06
    POSITIVE LOGITS
     Larson
    0.07
    _ov
    0.06
    hazi
    0.06
     ©
    0.06
    ');?>"
    0.06
     jerseys
    0.06
    "]="
    0.06
     directory
    0.06
    _LL
    0.06
     kre
    0.06
    Act Density 0.055%

    No Known Activations