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

    Neuronpedia

    INDEX
    Explanations

    html input hidden fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    のを
    1.35
     myśl
    1.28
     iba
    1.26
     neur
    1.26
     invari
    1.25
     inch
    1.25
     ral
    1.24
    WindowState
    1.23
     onc
    1.23
     ae
    1.22
    POSITIVE LOGITS
    𝐢
    1.49
    Lä
    1.42
    े
    1.34
    ์
    1.28
    aq
    1.28
    قی
    1.21
    Muchas
    1.21
    er
    1.19
    ात
    1.19
    particular
    1.19
    Act Density 0.000%

    No Known Activations