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

    Neuronpedia

    INDEX
    Explanations

    military experience, broadcasts, master suite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ద్ధి
    0.46
    A
    0.44
    カスタム
    0.43
    z
    0.42
    Mara
    0.42
    S
    0.42
    zad
    0.41
     chắn
    0.41
    衆
    0.41
    멩
    0.41
    POSITIVE LOGITS
     টুল
    0.47
     armon
    0.46
     Polaroid
    0.44
     snaps
    0.44
     erhö
    0.43
     scanners
    0.43
     ironic
    0.41
     solaire
    0.41
     aner
    0.40
     Claude
    0.40
    Act Density 0.005%

    No Known Activations