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

    Neuronpedia

    INDEX
    Explanations

    single, control, or alongside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ון
    0.44
    (
    0.41
    remia
    0.40
     (
    0.38
     জমা
    0.37
     custody
    0.36
    epid
    0.36
     convinc
    0.36
    ং
    0.36
    mson
    0.36
    POSITIVE LOGITS
    üşt
    0.42
     Gently
    0.41
    projectlombok
    0.40
    欴
    0.40
     Petite
    0.39
     volna
    0.39
     Codes
    0.38
     ngôn
    0.38
    পাড়
    0.38
     Single
    0.38
    Act Density 0.000%

    No Known Activations