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

    Neuronpedia

    INDEX
    Explanations

    aggression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    magnitude
    -0.07
     शक
    -0.07
     Whale
    -0.06
     предмет
    -0.06
     unequal
    -0.06
    えない
    -0.06
    úp
    -0.06
    -Russian
    -0.06
    coll
    -0.06
    Í
    -0.06
    POSITIVE LOGITS
     매우
    0.06
     Ook
    0.06
     recreate
    0.06
     små
    0.06
    .InputStreamReader
    0.06
    はい
    0.06
     Agricult
    0.06
     Zá
    0.06
     Islanders
    0.06
     Pref
    0.06
    Act Density 0.123%

    No Known Activations