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

    Neuronpedia

    INDEX
    Explanations

    words related to mental health, brains, and therapy

    oai_token-act-pair · gemini-2.0-flash

    Social behavior and psychology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     botellas
    -0.49
     nahilalakip
    -0.48
    İstinadlar
    -0.47
     limiti
    -0.47
    limitations
    -0.46
     limiting
    -0.44
     ceilings
    -0.44
     romántica
    -0.44
    限定
    -0.44
     cucharadas
    -0.44
    POSITIVE LOGITS
    InSection
    0.72
    findpost
    0.63
    expandindo
    0.62
    gameserver
    0.61
     EconPapers
    0.60
     empathy
    0.57
     socio
    0.56
     social
    0.56
    opathy
    0.54
    opathie
    0.54
    Act Density 1.286%

    No Known Activations