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

    Neuronpedia

    INDEX
    Explanations

    dev

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Instant
    -0.06
     nanny
    -0.06
     Initi
    -0.06
     средство
    -0.06
     Hip
    -0.06
    Lic
    -0.06
     Hogan
    -0.06
    economic
    -0.06
    สว
    -0.06
     PH
    -0.06
    POSITIVE LOGITS
    ."[
    0.07
    NTSTATUS
    0.07
     خودش
    0.07
     mistakenly
    0.06
     espect
    0.06
    تبر
    0.06
     Netanyahu
    0.06
    聘
    0.06
    schools
    0.06
     Maritime
    0.06
    Act Density 0.002%

    No Known Activations