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

    Neuronpedia

    INDEX
    Explanations

    front-end web development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỳnh
    0.78
    啭
    0.72
    flop
    0.71
    omatic
    0.68
    lepiej
    0.68
     भोजन
    0.67
     Pollock
    0.67
     xsi
    0.66
    㴌
    0.66
    Fizz
    0.66
    POSITIVE LOGITS
     end
    0.73
     angles
    0.71
     ends
    0.68
     End
    0.67
    layers
    0.66
     multilayer
    0.66
     stages
    0.65
     roundtable
    0.64
     enda
    0.63
    エンド
    0.63
    Act Density 0.053%

    No Known Activations