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

    Neuronpedia

    INDEX
    Explanations

    diverse text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VAR
    -0.07
     INPUT
    -0.06
    named
    -0.06
    emem
    -0.06
    .BAD
    -0.06
     youths
    -0.06
    characters
    -0.06
     Academic
    -0.06
     Going
    -0.06
     journalist
    -0.06
    POSITIVE LOGITS
    EmailAddress
    0.06
     performed
    0.06
    があり
    0.06
     choisir
    0.06
     işlet
    0.06
    dv
    0.06
    实验
    0.06
     attire
    0.06
     fulfill
    0.06
    .jwt
    0.06
    Act Density 0.000%

    No Known Activations