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

    Neuronpedia

    INDEX
    Explanations

    subconscious biases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    סטי
    0.38
     albo
    0.38
    чув
    0.37
     w
    0.36
     Che
    0.36
     cheques
    0.36
     pistes
    0.36
    Че
    0.36
     REQUI
    0.35
    sticks
    0.35
    POSITIVE LOGITS
     किसे
    0.40
     ആരാ
    0.39
     Sumatra
    0.39
     persuasive
    0.38
     뭐가
    0.37
    leys
    0.36
    いました
    0.36
     stricter
    0.36
    messer
    0.35
     kise
    0.35
    Act Density 0.000%

    No Known Activations