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

    Neuronpedia

    INDEX
    Explanations

    spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -validation
    -0.07
    ERTICAL
    -0.07
     OCR
    -0.07
     Zoe
    -0.07
    кі
    -0.06
     ATA
    -0.06
     도
    -0.06
     Vall
    -0.06
     hobby
    -0.06
     tumblr
    -0.06
    POSITIVE LOGITS
    /by
    0.06
    .WriteByte
    0.06
    ................................
    0.06
    !(
    0.06
     expans
    0.06
     Drama
    0.06
    faction
    0.06
    Serializable
    0.06
     awaiting
    0.06
    (inp
    0.06
    Act Density 0.004%

    No Known Activations