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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or ratings associated with films or media

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

    film release years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fread
    -0.63
     ſind
    -0.62
     IndexPath
    -0.60
    rinfo
    -0.59
    betic
    -0.59
     sube
    -0.58
     PyLong
    -0.58
    kenny
    -0.57
     deta
    -0.56
     Maxx
    -0.56
    POSITIVE LOGITS
     cokelat
    0.41
     clássico
    0.41
     karya
    0.40
    hdys
    0.38
    แดง
    0.38
     Verbrechen
    0.37
     clásico
    0.37
     scoperto
    0.36
     triomphe
    0.36
     estreia
    0.35
    Act Density 0.049%

    No Known Activations