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

    Neuronpedia

    INDEX
    Explanations

    asterisk character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cold
    -0.06
    payload
    -0.06
     OR
    -0.06
     لأن
    -0.06
    ुं
    -0.06
     edge
    -0.06
     움
    -0.06
     Treat
    -0.06
    .SUCCESS
    -0.06
    _small
    -0.06
    POSITIVE LOGITS
     represented
    0.07
    ecom
    0.06
    _rat
    0.06
    membership
    0.06
     DataService
    0.06
    ……………………
    0.06
     орган
    0.06
     брат
    0.06
    ام
    0.06
    laması
    0.06
    Act Density 0.003%

    No Known Activations