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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and commands related to programming or technical specifications

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

    C macro definitions

    np_acts-logits-general · gemini-2.0-flash

    `acr_task_delete`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.85
    ftagPool
    -0.59
    ispiel
    -0.59
     educativas
    -0.56
     ghz
    -0.56
     виправивши
    -0.55
    tráfico
    -0.53
     дописавши
    -0.52
     gọn
    -0.52
     Empieza
    -0.51
    POSITIVE LOGITS
     Diſ
    0.74
     Reſ
    0.73
     houſe
    0.69
    })));
    0.67
     Conſ
    0.66
     Inſ
    0.63
     Houſe
    0.61
     nakalista
    0.61
     ['./
    0.60
     Perſ
    0.59
    Act Density 0.303%

    No Known Activations