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

    Neuronpedia

    INDEX
    Explanations

    A introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conve
    0.44
    frac
    0.41
     fractions
    0.41
    лда
    0.40
     equating
    0.40
    ወሰ
    0.39
    commit
    0.39
     нема
    0.39
     Cu
    0.39
    값을
    0.38
    POSITIVE LOGITS
    టన
    0.41
    vgili
    0.41
    ચર
    0.40
    审美
    0.39
     favorites
    0.39
    ত্তি
    0.39
    ڑک
    0.38
    ivät
    0.38
     साधन
    0.37
     giants
    0.37
    Act Density 0.000%

    No Known Activations