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

    Neuronpedia

    INDEX
    Explanations

    numbers and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cosidd
    0.38
     kadang
    0.37
     manchmal
    0.36
     आपल्याला
    0.35
     graus
    0.35
     அல்லது
    0.34
     vaše
    0.34
    Assim
    0.34
    𝖊
    0.34
     parfois
    0.33
    POSITIVE LOGITS
    7
    0.32
    6
    0.31
    5
    0.31
     সাত
    0.30
     July
    0.30
     Tuesday
    0.29
     Method
    0.29
     Theorem
    0.29
     five
    0.29
     Three
    0.29
    Act Density 0.449%

    No Known Activations