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

    Neuronpedia

    INDEX
    Explanations

    lambda functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ventyConfig
    0.74
    猙
    0.70
     vscode
    0.69
    izoph
    0.69
     palju
    0.68
    locatorType
    0.67
    getUser
    0.66
    ématique
    0.66
     பேசு
    0.65
     wenige
    0.65
    POSITIVE LOGITS
     context
    0.47
    honey
    0.46
     overlapping
    0.46
     distinct
    0.46
     benefit
    0.45
     hobby
    0.45
     مد
    0.44
     overlap
    0.44
     heck
    0.43
    ২০
    0.43
    Act Density 0.001%

    No Known Activations