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

    Neuronpedia

    INDEX
    Explanations

    context words, becoming, microscopic, lethal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Baker
    0.43
    PHP
    0.41
    Jacob
    0.41
    jaw
    0.40
    ောက်ပ
    0.40
    Jaw
    0.40
     skil
    0.39
    Mountain
    0.38
     skillfully
    0.38
    NewCollection
    0.38
    POSITIVE LOGITS
     delicacy
    0.40
    erasan
    0.39
    ariously
    0.38
    finaly
    0.38
     Vary
    0.37
     transcendent
    0.36
    vegarde
    0.36
     emote
    0.35
     Regener
    0.35
     dissolve
    0.34
    Act Density 0.000%

    No Known Activations