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

    Neuronpedia

    INDEX
    Explanations

    alarming negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     technically
    0.57
     appreciate
    0.48
    分类
    0.45
     automatically
    0.44
     differentiate
    0.43
    ueta
    0.42
     physically
    0.41
     assurance
    0.41
    Classification
    0.40
     এতদিন
    0.40
    POSITIVE LOGITS
     insidious
    0.99
     Sadly
    0.95
    Sadly
    0.95
     sadly
    0.94
     pernicious
    0.92
     alarming
    0.91
     ominous
    0.89
     malaise
    0.86
     malheureusement
    0.84
     tragic
    0.81
    Act Density 0.014%

    No Known Activations