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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and sentiments expressing assistance or support

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

    bleeding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.64
    دانشنامهٔ
    -0.63
    amssymb
    -0.61
    RTGC
    -0.60
     HttpNotFound
    -0.60
     utafitiHapana
    -0.60
    zzleHttp
    -0.56
    Ӕ
    -0.55
    bukkit
    -0.55
     ſind
    -0.54
    POSITIVE LOGITS
     czerwony
    0.36
    czerw
    0.33
     llegará
    0.31
    SEGUIR
    0.31
     dreapta
    0.31
    뀔
    0.31
     decía
    0.31
     hablaba
    0.30
    Citiți
    0.30
    kách
    0.30
    Act Density 0.140%

    No Known Activations