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

    Neuronpedia

    INDEX
    Explanations

    storytelling and narrative explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.51
    +
    0.48
     marginalized
    0.46
     シンプル
    0.45
     Geheim
    0.45
    酚
    0.44
    čního
    0.44
     文化
    0.43
     قام
    0.43
    juk
    0.43
    POSITIVE LOGITS
     produto
    0.58
     exame
    0.50
    вища
    0.50
    method
    0.49
     ejec
    0.48
    contenido
    0.48
     produtos
    0.48
     monta
    0.47
     dola
    0.46
    টের
    0.46
    Act Density 0.001%

    No Known Activations