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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arc
    -0.07
    。本
    -0.07
     superstar
    -0.07
    sob
    -0.06
     repercussions
    -0.06
    ิป
    -0.06
    liers
    -0.06
     pledges
    -0.06
     pa
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    Converter
    0.07
     dependent
    0.06
    [\
    0.06
    _lane
    0.06
     foolish
    0.06
    _flutter
    0.06
     mac
    0.06
    الم
    0.06
    .IsActive
    0.06
    ordion
    0.06
    Act Density 0.100%

    No Known Activations