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

    Neuronpedia

    INDEX
    Explanations

    sensitivity to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ajah
    0.42
    ជាប់
    0.39
    uação
    0.38
     रिवा
    0.37
    cuda
    0.36
    خاب
    0.36
    jev
    0.36
    훈
    0.36
    bagian
    0.35
    vient
    0.35
    POSITIVE LOGITS
     sensitivity
    2.95
     sensitive
    2.92
     Sensitivity
    2.75
     чувстви
    2.73
    敏感
    2.70
    sensitive
    2.66
     Sensitive
    2.66
    Sensitivity
    2.64
    Sensitive
    2.56
     sensitivities
    2.52
    Act Density 0.048%

    No Known Activations