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

    Neuronpedia

    INDEX
    Explanations

    URL redirects and rewrites

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .skip
    -0.07
    olding
    -0.07
    anism
    -0.07
     vessel
    -0.07
    .ribbon
    -0.06
     Arlington
    -0.06
    )};↵
    -0.06
     yup
    -0.06
    Read
    -0.06
    .res
    -0.06
    POSITIVE LOGITS
     issuer
    0.07
     zaměst
    0.07
    .SpringBootApplication
    0.06
     πλα
    0.06
    0.06
    rew
    0.06
    .operator
    0.06
     yaşlı
    0.06
    рай
    0.06
    ()[
    0.06
    Act Density 0.056%

    No Known Activations