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

    Neuronpedia

    INDEX
    Explanations

    left foot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.54
    ।
    0.49
    be
    0.48
    func
    0.48
    cas
    0.47
    cb
    0.47
    ca
    0.47
    rb
    0.46
    bc
    0.46
    gal
    0.45
    POSITIVE LOGITS
    ргә
    0.51
    संख्या
    0.49
     обратно
    0.48
     conséquent
    0.46
     Vertex
    0.46
     stencil
    0.45
    ুটি
    0.44
    ғи
    0.43
     любовь
    0.42
    ાર્થ
    0.42
    Act Density 0.000%

    No Known Activations