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

    Neuronpedia

    INDEX
    Explanations

    Mot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silent
    -0.07
     nitel
    -0.06
    /XML
    -0.06
    negative
    -0.06
    Adam
    -0.06
    ID
    -0.06
     Nate
    -0.06
    ĐT
    -0.06
    -</
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    alli
    0.07
     хв
    0.06
    fea
    0.06
     slur
    0.06
     malware
    0.06
     실제
    0.06
    lığın
    0.06
     Residential
    0.06
     phối
    0.06
    циклоп
    0.06
    Act Density 0.000%

    No Known Activations