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

    Neuronpedia

    INDEX
    Explanations

    macros, target, defined roles, shift

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '$\
    0.39
    बेन
    0.38
    🌴
    0.38
    𝕕
    0.37
    getY
    0.37
     bhav
    0.36
     competencies
    0.36
    บ่ง
    0.36
     নেবার
    0.36
     winners
    0.36
    POSITIVE LOGITS
    Jump
    0.47
    跳
    0.44
     jump
    0.43
    jump
    0.42
     jumps
    0.41
     jumping
    0.40
    中間
    0.39
    UNK
    0.39
     ມີ
    0.38
     heats
    0.38
    Act Density 0.000%

    No Known Activations