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

    Neuronpedia

    INDEX
    Explanations

    Oops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SANT
    0.51
     بہترین
    0.45
    Sant
    0.44
    prakt
    0.41
    ऑ
    0.41
     życiu
    0.41
    ”…
    0.41
     sant
    0.40
    bald
    0.40
     সেরা
    0.39
    POSITIVE LOGITS
    ，
    0.49
    都需要
    0.47
     Obrador
    0.44
    -
    0.43
     Amendment
    0.43
    ћа
    0.43
     burdensome
    0.43
     Burden
    0.43
    াত
    0.43
     Divisions
    0.42
    Act Density 0.001%

    No Known Activations