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

    Neuronpedia

    INDEX
    Explanations

    offer APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adaptarse
    0.47
    执行
    0.41
    亚
    0.41
    主办
    0.40
     Adam
    0.40
     Mixed
    0.40
    ق
    0.39
     Tracking
    0.38
    烧
    0.38
    勲
    0.38
    POSITIVE LOGITS
    agl
    0.53
    ut
    0.49
    i
    0.49
     ಏಕೆ
    0.47
    ogl
    0.47
    an
    0.46
    agal
    0.46
    yog
    0.46
    og
    0.46
     gestational
    0.46
    Act Density 0.000%

    No Known Activations