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

    Neuronpedia

    INDEX
    Explanations

    BB followed by Edit, gun, VA, G

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    निश्
    0.39
    ckpt
    0.39
     временем
    0.39
     ive
    0.37
    ఎస్‌
    0.37
    enames
    0.37
     flywheel
    0.37
     extant
    0.37
    stoß
    0.37
     Construction
    0.36
    POSITIVE LOGITS
    ông
    0.45
    м
    0.40
    禁止
    0.36
     '//
    0.36
    ichtig
    0.36
    <0xA0>
    0.35
    olog
    0.35
    encia
    0.35
    oldCount
    0.35
    old
    0.34
    Act Density 0.001%

    No Known Activations