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

    Neuronpedia

    INDEX
    Explanations

    intervention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylum
    -0.07
     №
    -0.06
    -*-
    -0.06
    UNITY
    -0.06
    ักษ
    -0.06
     ít
    -0.06
    ISTRIBUT
    -0.06
    нула
    -0.06
     HOL
    -0.06
    ітет
    -0.06
    POSITIVE LOGITS
     adolescente
    0.06
     seo
    0.06
    (ctrl
    0.06
     bio
    0.06
    .Or
    0.06
     gambling
    0.06
     tokenizer
    0.06
     ihrer
    0.06
    .clips
    0.06
    .say
    0.06
    Act Density 0.011%

    No Known Activations