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

    Neuronpedia

    INDEX
    Explanations

    you followed by ' or might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.34
     hacerse
    0.31
    \(
    0.29
    $("
    0.29
    การ
    0.29
    𝘴
    0.28
    $
    0.28
     columnIndex
    0.27
    szer
    0.27
    是为了
    0.27
    POSITIVE LOGITS
    en
    0.46
    на
    0.37
    д
    0.37
    ق
    0.36
    राधिक
    0.33
    ర్జాతీయ
    0.33
     ज्ञापन
    0.33
    ूस
    0.33
     oxide
    0.32
     شورای
    0.32
    Act Density 0.423%

    No Known Activations