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

    Neuronpedia

    INDEX
    Explanations

    Sexual content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cars
    -0.07
    ��
    -0.06
    logic
    -0.06
     rowspan
    -0.06
    ringe
    -0.06
    .apps
    -0.06
    _MEDIA
    -0.06
    dependence
    -0.06
    ']>;↵
    -0.06
     Terrorism
    -0.06
    POSITIVE LOGITS
     Nich
    0.06
     Nu
    0.06
     Deniz
    0.06
    ags
    0.06
     Maintain
    0.06
    _FD
    0.06
     objectId
    0.06
     Phong
    0.06
     risks
    0.06
     цик
    0.06
    Act Density 0.074%

    No Known Activations