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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     congé
    0.40
    }):=\
    0.36
     PL
    0.36
     />;
    0.35
     upscale
    0.35
     ovip
    0.35
     pampered
    0.34
    ړو
    0.34
     ore
    0.34
     prepd
    0.34
    POSITIVE LOGITS
    Glucose
    0.41
    VR
    0.40
    akan
    0.39
     VR
    0.38
    πει
    0.38
    Raising
    0.37
    𝟏
    0.37
    aft
    0.36
    illing
    0.36
    ede
    0.36
    Act Density 0.000%

    No Known Activations