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

    Neuronpedia

    INDEX
    Explanations

    verbs

    np_max-act · gemini-2.0-flash

    words expressing causal impact or influence (e.g. verbs like “exacerbate,” “impede,” “encourage,” “hurt,” “devalue,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     веч
    -0.06
    ircular
    -0.06
     solve
    -0.06
    oor
    -0.06
     такие
    -0.06
    cers
    -0.06
    CW
    -0.06
    imated
    -0.06
     visas
    -0.06
     dolls
    -0.06
    POSITIVE LOGITS
    .Ge
    0.07
    /business
    0.07
     haciendo
    0.07
     ек
    0.06
     oppon
    0.06
     воно
    0.06
     shipment
    0.06
    Exchange
    0.06
    ющие
    0.06
     jiných
    0.06
    Act Density 0.096%

    No Known Activations