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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เด
    -0.06
    ulu
    -0.06
     lesbisk
    -0.06
    蕉
    -0.06
     feet
    -0.06
    Girls
    -0.06
    pitch
    -0.06
    xde
    -0.06
    _notice
    -0.06
     pisc
    -0.06
    POSITIVE LOGITS
     ExecutionContext
    0.07
     Torrent
    0.07
    irth
    0.07
    -ups
    0.07
    ".
    0.07
    >>↵↵
    0.06
     lenght
    0.06
     banned
    0.06
    ision
    0.06
    cit
    0.06
    Act Density 0.021%

    No Known Activations