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

    Neuronpedia

    INDEX
    Explanations

    relatively flatness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ális
    0.45
     سریع
    0.43
     indiquée
    0.43
     außerhalb
    0.42
     verlassen
    0.41
    閻
    0.41
     착
    0.40
    jach
    0.40
    czych
    0.40
     esqu
    0.39
    POSITIVE LOGITS
    Syn
    0.52
    कल्चर
    0.46
     Mahi
    0.46
     रिले
    0.46
    Moore
    0.45
    AMES
    0.44
    Poly
    0.43
    t
    0.43
    Effect
    0.42
     hasher
    0.42
    Act Density 0.000%

    No Known Activations