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

    Neuronpedia

    INDEX
    Explanations

    CSS styling properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🩹
    0.48
     Johanna
    0.46
     COSTS
    0.46
     сохрани
    0.46
     getDefault
    0.45
     subspaces
    0.44
    வதி
    0.44
    🍘
    0.44
    🧉
    0.44
     Posterior
    0.43
    POSITIVE LOGITS
    //
    0.92
    for
    0.73
    return
    0.70
    if
    0.68
    #
    0.68
    });
    0.61
    let
    0.61
    line
    0.59
    /*
    0.58
    --
    0.57
    Act Density 0.013%

    No Known Activations