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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

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

    Mathematical simplification/algebra problems

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }{@
    -0.67
     Logement
    -0.60
     Inflate
    -0.54
    addCriterion
    -0.54
     Dès
    -0.54
     gekle
    -0.54
     faisons
    -0.54
    kloped
    -0.54
     saites
    -0.53
    HttpPut
    -0.52
    POSITIVE LOGITS
     Show
    0.71
    Show
    0.64
     SHOW
    0.64
    show
    0.61
     show
    0.61
    HINT
    0.60
     Jus
    0.59
    Hint
    0.58
    PasswordEncoder
    0.57
    Hints
    0.56
    Act Density 1.709%

    No Known Activations