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

    Neuronpedia

    INDEX
    Explanations

    Unfortunately, not possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Boundary
    0.42
     Blowing
    0.41
     Viewing
    0.41
     Typically
    0.40
     vegetarian
    0.40
     lefty
    0.40
    Boundary
    0.38
     any
    0.38
     शून्य
    0.38
     Divid
    0.38
    POSITIVE LOGITS
     moeilijk
    0.48
     трудно
    0.48
     труд
    0.47
     moeil
    0.45
     продаж
    0.38
     énorm
    0.37
    liy
    0.37
    reira
    0.37
    这也是
    0.37
    addAlignment
    0.37
    Act Density 0.001%

    No Known Activations