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

    Neuronpedia

    INDEX
    Explanations

    software and platform technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    കേന്ദ്രം
    0.71
     ហើយ
    0.70
     其中
    0.69
    <unused1071>
    0.66
    ibirsk
    0.66
    𝐫
    0.65
    <unused584>
    0.64
    <unused1130>
    0.64
    <unused561>
    0.64
    <unused315>
    0.63
    POSITIVE LOGITS
    ک
    0.75
    다
    0.73
    க
    0.65
    ↵
    0.63
    고
    0.63
    제
    0.59
    Dec
    0.59
    There
    0.59
    हा
    0.57
    अ
    0.56
    Act Density 0.307%

    No Known Activations