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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sweeps
    0.46
     spherical
    0.42
     buffs
    0.42
     sweep
    0.41
     comfy
    0.40
     carb
    0.40
     swivel
    0.40
     icy
    0.39
    thro
    0.39
     cluster
    0.39
    POSITIVE LOGITS
    PERMISSION
    0.49
    améliorer
    0.46
    嵇
    0.44
     accedere
    0.44
    姉
    0.43
    籹
    0.42
    耋
    0.42
    nivers
    0.42
     پروف
    0.41
    Rail
    0.41
    Act Density 0.014%

    No Known Activations