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

    Neuronpedia

    INDEX
    Explanations

    desire, need, positioning, shine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bamb
    0.47
    ┑
    0.43
     spaceShip
    0.43
     پول
    0.43
     einmal
    0.42
    インタ
    0.42
    គ្រឿង
    0.41
    ড়ের
    0.41
     pamię
    0.41
    鉆
    0.41
    POSITIVE LOGITS
     hyp
    0.37
    '
    0.37
    abler
    0.37
     Hooper
    0.36
    0.35
    fulness
    0.35
    eto
    0.35
    stift
    0.35
    imed
    0.34
    -
    0.34
    Act Density 0.000%

    No Known Activations