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

    Neuronpedia

    INDEX
    Explanations

    putative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.80
     hesitation
    -0.60
     faciles
    -0.59
     '\\;'
    -0.59
    Portale
    -0.58
     Sikhs
    -0.58
     nervioso
    -0.57
    Geplaatst
    -0.57
     chaude
    -0.57
     carelessness
    -0.57
    POSITIVE LOGITS
    ness
    0.69
    dro
    0.63
    NESS
    0.60
    downs
    0.59
     Dro
    0.58
    addCriterion
    0.57
    .}\
    0.56
     outputStream
    0.54
    nesses
    0.53
     {},
    0.53
    Act Density 0.058%

    No Known Activations