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

    Neuronpedia

    INDEX
    Explanations

    twist variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HF
    0.42
    Workflow
    0.42
     জীববিজ্ঞান
    0.42
    FFEE
    0.40
    Donor
    0.40
    割り
    0.40
    ✍
    0.40
    Animating
    0.39
    Palm
    0.39
    一般的な
    0.39
    POSITIVE LOGITS
     sister
    0.48
     s
    0.47
     apreci
    0.47
     variants
    0.46
     munitions
    0.45
     su
    0.44
     meet
    0.44
     soph
    0.43
     variante
    0.43
     become
    0.43
    Act Density 0.001%

    No Known Activations