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

    Neuronpedia

    INDEX
    Explanations

    connections and disconnection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stain
    0.87
     prerogative
    0.87
    নায়
    0.86
    ൂർ
    0.84
    Chorus
    0.84
    ilai
    0.83
    रोवर
    0.82
    期
    0.80
     nah
    0.80
    籁
    0.79
    POSITIVE LOGITS
     برقرار
    1.25
    icut
    1.13
     বিচ্ছিন্ন
    1.10
     끊
    1.09
     severed
    1.08
     wang
    1.05
    শিপ
    1.04
    IVITY
    1.02
    ivities
    1.01
    끊
    0.98
    Act Density 0.210%

    No Known Activations