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

    Neuronpedia

    INDEX
    Explanations

    comes in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    棄
    0.87
     manio
    0.80
     बताए
    0.75
    Warn
    0.75
     manoeuvre
    0.74
    ơ
    0.74
     ڈال
    0.73
    িপ
    0.71
     डाले
    0.71
     manoe
    0.70
    POSITIVE LOGITS
     consigo
    1.19
     forth
    1.08
     létre
    0.99
    ો
    0.96
    値
    0.94
     flooding
    0.93
     Defining
    0.92
     gelen
    0.88
     defining
    0.87
     brought
    0.85
    Act Density 0.060%

    No Known Activations