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

    Neuronpedia

    INDEX
    Explanations

    references to notable artists and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    artist and creator accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bigliamento
    -0.38
    UnitTesting
    -0.36
    GEBURTSDATUM
    -0.36
     Wissenschaften
    -0.36
     ayudar
    -0.34
    uxxxx
    -0.33
     Evaluación
    -0.32
     EVALUATION
    -0.32
    Viited
    -0.31
     stanga
    -0.31
    POSITIVE LOGITS
     experimented
    0.60
     experimenting
    0.59
     작업
    0.57
     pioneered
    0.57
     prefers
    0.57
    AddTagHelper
    0.56
     explores
    0.55
     specializes
    0.54
     experiments
    0.53
     lavori
    0.53
    Act Density 0.052%

    No Known Activations