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

    Neuronpedia

    INDEX
    Explanations

    exploits and vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     druž
    -0.07
    Bed
    -0.07
     Anything
    -0.07
    сион
    -0.07
    igInteger
    -0.06
    _guide
    -0.06
    atives
    -0.06
    onu
    -0.06
     Liability
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    mayı
    0.06
    i�
    0.06
     tame
    0.06
    �
    0.06
    _archive
    0.06
    �
    0.06
     Subjects
    0.06
     pohy
    0.06
     defaults
    0.05
    411
    0.05
    Act Density 0.032%

    No Known Activations