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

    Neuronpedia

    INDEX
    Explanations

    say "dro" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OPEN
    -0.06
    -valid
    -0.06
     έναν
    -0.06
    EEEE
    -0.06
    ITIONAL
    -0.06
    Submit
    -0.06
    onor
    -0.06
    Repositories
    -0.06
     tucked
    -0.06
     pady
    -0.06
    POSITIVE LOGITS
     města
    0.07
    _genre
    0.06
     canadian
    0.06
     abbiamo
    0.06
     Has
    0.06
    .cloudflare
    0.06
    /logger
    0.06
    意义
    0.06
    rose
    0.06
     石
    0.06
    Act Density 0.001%

    No Known Activations