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

    Neuronpedia

    INDEX
    Explanations

    Mobile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ravel
    -0.07
    vre
    -0.06
    _PLAY
    -0.06
     Labour
    -0.06
    cov
    -0.06
    >_
    -0.06
    olver
    -0.06
    했던
    -0.06
    (indent
    -0.06
     disob
    -0.06
    POSITIVE LOGITS
    features
    0.06
    Candidates
    0.06
     Read
    0.06
     imprisoned
    0.06
     плат
    0.06
    .generate
    0.06
     Based
    0.06
    }
↵
↵
↵
    0.06
     pipelines
    0.06
    paid
    0.06
    Act Density 0.004%

    No Known Activations