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

    Neuronpedia

    INDEX
    Explanations

    uniform real distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onte
    0.41
    ĺ
    0.40
    ococ
    0.39
    Ꮔ
    0.39
    gifter
    0.38
    iéndose
    0.38
    iremos
    0.38
     warrants
    0.38
     नागल
    0.38
    邸
    0.38
    POSITIVE LOGITS
     UU
    0.58
     U
    0.58
     UF
    0.56
     UW
    0.55
     UB
    0.54
     Uw
    0.54
     uu
    0.53
     UM
    0.52
     u
    0.51
     UH
    0.50
    Act Density 0.069%

    No Known Activations