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

    Neuronpedia

    INDEX
    Explanations

    equivalent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lak
    -0.08
     nogal
    -0.08
     prevents
    -0.08
     interfering
    -0.07
     witches
    -0.07
    !↵↵↵↵
    -0.07
     overdose
    -0.07
    anasan
    -0.07
     inhib
    -0.07
     influences
    -0.07
    POSITIVE LOGITS
    とな
    0.09
     miniature
    0.08
     möjlighet
    0.08
     Möglichkeit
    0.08
     называется
    0.08
    ுமான
    0.07
     utama
    0.07
     يسمى
    0.07
    iup
    0.07
     Yen
    0.07
    Act Density 0.032%

    No Known Activations