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

    Neuronpedia

    INDEX
    Explanations

    types of writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bone
    0.53
     later
    0.50
     attend
    0.47
     sympat
    0.46
     relic
    0.46
     back
    0.46
     resident
    0.45
     swab
    0.45
     participate
    0.44
     scout
    0.44
    POSITIVE LOGITS
    מ
    0.55
    לב
    0.50
    平成
    0.48
    ֆ
    0.48
    COMMAND
    0.47
    ני
    0.47
    يح
    0.47
    粵
    0.46
    אס
    0.46
    𝐄
    0.46
    Act Density 0.001%

    No Known Activations