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

    Neuronpedia

    INDEX
    Explanations

    travel locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selenium
    -0.07
     topic
    -0.06
    ektiv
    -0.06
    roupe
    -0.06
     credible
    -0.06
     Selenium
    -0.06
     karakter
    -0.06
     Tomb
    -0.06
     pedigree
    -0.06
     cannot
    -0.06
    POSITIVE LOGITS
    拜
    0.07
    (comm
    0.07
     슬
    0.07
    ��
    0.06
    เห
    0.06
    -cycle
    0.06
    _ws
    0.06
     конце
    0.06
    _DECL
    0.06
     \'
    0.06
    Act Density 0.008%

    No Known Activations