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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LD
    -0.07
    32
    -0.07
    .v
    -0.07
     Somebody
    -0.06
    Tab
    -0.06
    12
    -0.06
     Scheduler
    -0.06
     RF
    -0.06
    โด
    -0.06
     Dialogue
    -0.06
    POSITIVE LOGITS
     hashlib
    0.07
     influenced
    0.06
    ivated
    0.06
    ايا
    0.06
     واحد
    0.06
     caused
    0.06
     ifade
    0.06
    dül
    0.06
    чива
    0.06
    ")},↵
    0.06
    Act Density 0.005%

    No Known Activations