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

    Neuronpedia

    INDEX
    Explanations

    strength and durability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ö
    0.59
    وم
    0.48
    ઓને
    0.47
    𝐨
    0.47
    氳
    0.47
    um
    0.46
    artment
    0.45
    蝴
    0.45
    ностей
    0.44
    ård
    0.44
    POSITIVE LOGITS
     chaf
    0.53
     inhibitory
    0.52
     jurors
    0.52
     ப
    0.49
     antibacterial
    0.48
     astring
    0.48
     fighters
    0.48
     little
    0.48
     durability
    0.47
     emitters
    0.47
    Act Density 0.254%

    No Known Activations