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

    Neuronpedia

    INDEX
    Explanations

    identifying organizations and departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused242>
    0.32
    绁
    0.31
    اردوش
    0.30
    𒊏
    0.30
    <unused710>
    0.30
    楦
    0.29
    <unused279>
    0.29
    urètre
    0.29
    <unused309>
    0.28
    粞
    0.28
    POSITIVE LOGITS
     of
    0.37
     de
    0.35
     the
    0.35
    a
    0.34
    ,
    0.34
     A
    0.33
     for
    0.33
     a
    0.32
    0.32
     to
    0.31
    Act Density 0.025%

    No Known Activations