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

    Neuronpedia

    INDEX
    Explanations

    code blocks and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     να
    0.28
     подс
    0.28
     яким
    0.26
     adenos
    0.25
     большим
    0.25
     μέρος
    0.25
    жным
    0.24
    那边
    0.24
     dlatego
    0.24
     विषा
    0.24
    POSITIVE LOGITS
                            
    0.32
     unfolds
    0.32
        
    0.31
     .,
    0.31
    0.30
    수록
    0.29
    first
    0.28
    enders
    0.28
            
    0.28
               
    0.28
    Act Density 0.158%

    No Known Activations