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

    Neuronpedia

    INDEX
    Explanations

    cassandra

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seva
    0.59
     circun
    0.58
    শ্ব
    0.56
    proliferation
    0.55
    эр
    0.55
    urf
    0.55
    velopment
    0.55
    тивной
    0.54
     utilise
    0.53
    whale
    0.53
    POSITIVE LOGITS
     仕事
    0.74
     Cass
    0.64
    Cass
    0.64
     cass
    0.63
     ポー
    0.63
    cass
    0.61
     ประ
    0.59
     spits
    0.59
    cassandra
    0.58
     stagione
    0.57
    Act Density 0.000%

    No Known Activations