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

    Neuronpedia

    INDEX
    Explanations

    connection to or with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prerogative
    0.88
    ilai
    0.84
     nah
    0.83
    籁
    0.83
    ൂർ
    0.80
    Chorus
    0.80
    期
    0.80
    ীম
    0.80
    ट्
    0.80
    रोवर
    0.80
    POSITIVE LOGITS
     برقرار
    1.30
    icut
    1.24
     severed
    1.17
     끊
    1.12
    nection
    1.11
     বিচ্ছিন্ন
    1.09
    শিপ
    1.07
    ivities
    1.05
    nections
    1.04
     בין
    1.02
    Act Density 0.331%

    No Known Activations