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

    Neuronpedia

    INDEX
    Explanations

    sensory experiences described as like something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consideramos
    0.36
     ماشینونو
    0.33
     Revealed
    0.33
     بدون
    0.32
     Reveals
    0.32
     Changes
    0.32
     Considerations
    0.32
    மய
    0.31
     निचे
    0.31
     Vers
    0.31
    POSITIVE LOGITS
     like
    1.49
    像是
    1.11
     seperti
    1.06
    like
    1.05
    Like
    1.01
     مثل
    1.01
    像
    1.01
     LIKE
    1.00
     Like
    1.00
    เหมือน
    0.95
    Act Density 0.036%

    No Known Activations