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

    Neuronpedia

    INDEX
    Explanations

    questions asking why or how long

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    沔
    0.40
     Confirm
    0.39
    correct
    0.38
    Также
    0.38
    correcto
    0.38
     confirm
    0.37
    innaker
    0.36
     Также
    0.36
    연
    0.36
    assurer
    0.36
    POSITIVE LOGITS
     containment
    0.42
    ខ្ល
    0.40
     administra
    0.40
     refinery
    0.39
     divor
    0.38
     saline
    0.38
     geometri
    0.38
     lys
    0.38
    很难
    0.38
     exiled
    0.38
    Act Density 0.000%

    No Known Activations