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

    Neuronpedia

    INDEX
    Explanations

    EMIEW two or six

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🥅
    0.38
    LEXPORT
    0.38
    ᴸ
    0.36
    కార
    0.35
    ິ
    0.35
    覬
    0.34
    ಸ್ಯ
    0.34
    但是在
    0.34
    早就
    0.33
     لکھ
    0.33
    POSITIVE LOGITS
     voltage
    0.42
     daisy
    0.40
     ohms
    0.39
     gyro
    0.39
     silicon
    0.39
     compat
    0.38
     véhicules
    0.38
     gear
    0.38
     beam
    0.38
     voltages
    0.38
    Act Density 0.000%

    No Known Activations