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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     earlier
    -0.07
    flies
    -0.07
    -ne
    -0.07
     other
    -0.07
    esters
    -0.07
     tuned
    -0.07
    шие
    -0.07
     roses
    -0.07
     дод
    -0.07
     Technique
    -0.07
    POSITIVE LOGITS
    çu
    0.07
     appBar
    0.07
    noinspection
    0.06
     đúng
    0.06
     Higgins
    0.06
     JSBracketAccess
    0.06
    َج
    0.05
     ejaculation
    0.05
    وقع
    0.05
     keto
    0.05
    Act Density 0.011%

    No Known Activations