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

    Neuronpedia

    INDEX
    Explanations

    file (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BAD
    0.38
     Ol
    0.38
     InputListener
    0.36
    PSR
    0.35
    केशन
    0.35
    inist
    0.34
     पंजीकरण
    0.34
     Bumble
    0.34
    adillo
    0.34
     दै
    0.34
    POSITIVE LOGITS
     Cosmos
    0.40
     Mur
    0.39
     Victory
    0.39
     victorias
    0.38
    Cos
    0.38
     App
    0.38
    Lys
    0.37
     g
    0.37
    proc
    0.37
    Mur
    0.36
    Act Density 0.008%

    No Known Activations