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

    Neuronpedia

    INDEX
    Explanations

    synerg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pole
    -0.07
    셑
    -0.07
    珝
    -0.07
    配电
    -0.06
     gồm
    -0.06
     miesię
    -0.06
    .elementAt
    -0.06
    맀
    -0.06
    耶�
    -0.06
    逢
    -0.06
    POSITIVE LOGITS
     realise
    0.07
    .getField
    0.07
     empath
    0.07
     appended
    0.07
     trò
    0.07
    子女
    0.07
     resign
    0.07
    客户的
    0.07
    clf
    0.07
    (json
    0.07
    Act Density 0.003%

    No Known Activations