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

    Neuronpedia

    INDEX
    Explanations

    Two or more people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bakan
    -0.07
    ��제
    -0.07
    ǎ
    -0.06
    ران
    -0.06
    getContext
    -0.06
     demir
    -0.06
     [],
↵
    -0.06
    sın
    -0.06
    脸
    -0.06
    _CTL
    -0.06
    POSITIVE LOGITS
     Trigger
    0.07
     xương
    0.07
     varieties
    0.06
     μέχρι
    0.06
     місця
    0.06
    minus
    0.06
     Strange
    0.06
     accessing
    0.06
    افية
    0.06
    lete
    0.06
    Act Density 0.144%

    No Known Activations