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

    Neuronpedia

    INDEX
    Explanations

    pizza soggy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ऑर्गेनाइजेशन
    0.53
    evaluate
    0.53
     piloted
    0.51
    Kc
    0.50
    aeskeygenassist
    0.49
    pilot
    0.48
     ތ
    0.48
    packer
    0.48
     الاقتصاد
    0.48
    Context
    0.48
    POSITIVE LOGITS
    ة
    0.50
    า
    0.48
    子の
    0.47
    tenham
    0.46
     streak
    0.45
    은
    0.45
    না
    0.44
    한
    0.44
    нах
    0.44
    ս
    0.42
    Act Density 0.000%

    No Known Activations