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

    Neuronpedia

    INDEX
    Explanations

    seduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clazz
    -0.06
    .flowLayoutPanel
    -0.06
     VB
    -0.06
     yelled
    -0.06
     فلس
    -0.06
    ẵ
    -0.06
     run
    -0.06
     ran
    -0.06
    HasKey
    -0.06
     каз
    -0.06
    POSITIVE LOGITS
    du
    0.07
    darwin
    0.07
     Next
    0.07
    cue
    0.07
    öt
    0.07
     bạn
    0.06
     tempt
    0.06
    .productId
    0.06
     inducing
    0.06
     ked
    0.06
    Act Density 0.007%

    No Known Activations