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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating need or desire

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

    "para" or "pour" (Spanish/French)

    np_acts-logits-general · gemini-2.0-flash

    French and Spanish prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.74
     חיצוניים
    -0.60
    ర్య
    -0.59
    çoivent
    -0.58
     habido
    -0.58
     hjäl
    -0.57
    jména
    -0.57
    rungsseite
    -0.55
     Ate
    -0.54
     تانيه
    -0.53
    POSITIVE LOGITS
     be
    0.73
     prove
    0.60
    hasMoreElements
    0.59
    USDT
    0.57
    UrlResolution
    0.57
    ellees
    0.56
    ]=>
    0.55
     Responder
    0.54
    setopt
    0.54
    PathVariable
    0.53
    Act Density 0.082%

    No Known Activations