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

    Neuronpedia

    INDEX
    Explanations

    chili, preschool, dictionary, firm, witch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tracing
    0.52
    com
    0.48
    or
    0.46
     Alvarez
    0.46
    ären
    0.46
     cheated
    0.46
     Ksh
    0.46
    1
    0.46
     Remark
    0.46
     Sich
    0.46
    POSITIVE LOGITS
    醗
    0.62
     yếu
    0.55
    ಲ್ಯಾ
    0.54
    業務用
    0.51
    ی
    0.50
    ፌ
    0.50
     φορ
    0.49
    گی
    0.49
    我们的
    0.48
    િતિ
    0.48
    Act Density 0.001%

    No Known Activations