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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing actions or states of being

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

    "going on"

    np_acts-logits-general · gemini-2.0-flash

    going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ède
    -0.56
    Попис
    -0.54
    iseks
    -0.53
     Spisak
    -0.52
    Décès
    -0.52
     bandeja
    -0.52
    JNIEnv
    -0.51
    esModule
    -0.51
     Schulte
    -0.51
     Heine
    -0.50
    POSITIVE LOGITS
    Clik
    0.61
     AssemblyTitle
    0.56
    StructEnd
    0.55
     NUKAT
    0.53
    RectangleBorder
    0.52
    go
    0.52
    hyrchwyd
    0.52
    gog
    0.51
     wrong
    0.50
    StoreMessageInfo
    0.49
    Act Density 0.092%

    No Known Activations