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

    Neuronpedia

    INDEX
    Explanations

    directory traversal, concealer, amendment, equation, fourth planet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OOL
    1.41
    ಿಕ
    1.39
    weathermap
    1.33
    CLES
    1.30
    \}\
    1.29
    지와
    1.28
    רה
    1.27
    tering
    1.26
     greetings
    1.25
     gaseous
    1.23
    POSITIVE LOGITS
     불구하고
    1.64
    га
    1.55
    л
    1.55
    س
    1.52
    ara
    1.49
        
    1.43
    ח
    1.43
    ت
    1.41
    એ
    1.40
    og
    1.39
    Act Density 0.001%

    No Known Activations