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

    Neuronpedia

    INDEX
    Explanations

    a disruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     goto
    0.43
     ForeignKey
    0.41
     lateinit
    0.40
     NSLog
    0.40
    anmoins
    0.39
     conditioned
    0.39
     Goto
    0.38
     Reflex
    0.38
     Tetrahedron
    0.37
    따
    0.37
    POSITIVE LOGITS
     souls
    0.40
    sou
    0.39
    Sou
    0.38
    Shr
    0.37
    shr
    0.36
     din
    0.36
    пле
    0.35
     oor
    0.35
    Ụ
    0.35
    েম
    0.34
    Act Density 0.000%

    No Known Activations