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

    Neuronpedia

    INDEX
    Explanations

    Poetry and emotional writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ataques
    -0.08
     supports
    -0.07
     voters
    -0.07
     Frequency
    -0.07
     Carte
    -0.07
     vergonha
    -0.07
     Concurrent
    -0.07
    rape
    -0.07
    ρο
    -0.07
    ുന്നതിന
    -0.07
    POSITIVE LOGITS
     словно
    0.09
     countless
    0.09
     โลก
    0.08
     삶
    0.08
     sigh
    0.08
     maailma
    0.08
    imat
    0.08
    awah
    0.08
     penned
    0.08
     contemplating
    0.08
    Act Density 0.194%

    No Known Activations