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

    Neuronpedia

    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apos
    -0.29
     onPostExecute
    -0.28
    adden
    -0.26
     undis
    -0.26
    ayload
    -0.25
    preg
    -0.25
    VES
    -0.25
     anything
    -0.25
    cept
    -0.24
    nnen
    -0.24
    POSITIVE LOGITS
     scarcity
    0.26
    ç¹ģåįİ
    0.26
    æĦıåij³
    0.25
    å¹³åı°ä¸Ĭ
    0.25
    _capability
    0.25
    åķ¬
    0.25
     thirsty
    0.25
    _ber
    0.24
    ROME
    0.24
    antha
    0.24
    Act Density 0.004%

    No Known Activations