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

    Neuronpedia

    INDEX
    Explanations

    YouTube explains common issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    둴
    0.53
    stylers
    0.51
    सुम
    0.51
    pośred
    0.50
    ন্ধ
    0.50
     continúa
    0.49
     হয়
    0.49
    嘍
    0.49
    numericUpDown
    0.49
    spers
    0.48
    POSITIVE LOGITS
    BN
    0.43
     determining
    0.43
    :
    0.42
    CS
    0.38
    (
    0.38
    MP
    0.37
    igen
    0.37
    American
    0.37
     textbook
    0.37
    EL
    0.36
    Act Density 0.001%

    No Known Activations