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

    Neuronpedia

    INDEX
    Explanations

    programming context, code actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ங்கரை
    0.44
    ovce
    0.40
    แอ
    0.40
     माइनस
    0.39
    attes
    0.38
    oodle
    0.38
    точно
    0.37
     தூ
    0.37
    ലോക
    0.37
    दीय
    0.37
    POSITIVE LOGITS
     Strengthen
    0.40
     DROP
    0.38
     TBA
    0.37
     Hydra
    0.37
     유지
    0.36
    drop
    0.36
    強化
    0.36
     gota
    0.35
     Reise
    0.35
     inferior
    0.34
    Act Density 0.001%

    No Known Activations