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

    Neuronpedia

    INDEX
    Explanations

    states and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dvara
    0.92
    Cómo
    0.84
    갤
    0.80
     fleurs
    0.79
    Jeśli
    0.79
     dimensioni
    0.78
     principali
    0.77
     mécanismes
    0.77
    ના
    0.76
    க்
    0.75
    POSITIVE LOGITS
     Plain
    0.79
     wiggle
    0.79
     Vendor
    0.75
     Installing
    0.73
     Advis
    0.72
     Stewardship
    0.71
     Visible
    0.71
     полный
    0.70
     Ward
    0.70
     Advertising
    0.70
    Act Density 0.003%

    No Known Activations