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

    Neuronpedia

    INDEX
    Explanations

    beyond visual range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urare
    0.41
    hkse
    0.40
     Editing
    0.39
    Pol
    0.39
    marginStart
    0.38
    hole
    0.38
     TextStyle
    0.37
    länder
    0.37
     Sentencing
    0.37
     অনুপ
    0.36
    POSITIVE LOGITS
    oflavin
    0.40
     observatory
    0.40
     pector
    0.39
     imani
    0.38
     erecting
    0.38
     longs
    0.38
     Altos
    0.37
     issu
    0.37
     supporting
    0.35
     samb
    0.35
    Act Density 0.000%

    No Known Activations