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

    Neuronpedia

    INDEX
    Explanations

    average annual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iveness
    0.39
    fulness
    0.38
    ires
    0.36
     gusto
    0.36
    comfort
    0.35
    ide
    0.35
    кали
    0.35
    vers
    0.35
    cles
    0.34
    surprise
    0.34
    POSITIVE LOGITS
    每年
    0.45
     oWord
    0.44
     BOOL
    0.42
    ম্
    0.40
    厰
    0.40
     actitudes
    0.39
    ړئ
    0.38
     sodio
    0.38
     saddhim
    0.38
     adjoining
    0.38
    Act Density 0.000%

    No Known Activations