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

    Neuronpedia

    INDEX
    Explanations

    Long strings of dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    ราช
    -0.07
     dedic
    -0.07
    -0.07
     Osaka
    -0.07
    ;;;
    -0.07
     meas
    -0.07
    -0.06
     plais
    -0.06
    -0.06
    POSITIVE LOGITS
    ----------------
    0.28
    ────────
    0.08
    //----------------
    0.08
    ("----------------
    0.07
    erusform
    0.07
    ────
    0.06
     //----------------
    0.06
     cripp
    0.06
    maması
    0.06
     strtotime
    0.06
    Act Density 0.002%

    No Known Activations