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

    Neuronpedia

    INDEX
    Explanations

    according to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    accion
    0.54
    items
    0.50
    商城
    0.50
     தனது
    0.49
    트
    0.49
    window
    0.48
     ganado
    0.46
     Lazada
    0.45
    escape
    0.45
     Azerbai
    0.45
    POSITIVE LOGITS
    Mineral
    0.49
    Chemistry
    0.46
    HIP
    0.44
     predecess
    0.43
    olisme
    0.42
     costit
    0.42
    Dimethyl
    0.42
    ளிலும்
    0.41
    笏
    0.41
     profondes
    0.41
    Act Density 0.006%

    No Known Activations