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

    Neuronpedia

    INDEX
    Explanations

    after/following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Viktor
    -0.07
     Jesus
    -0.07
    Wolf
    -0.07
    させ
    -0.07
     Iterator
    -0.07
    Jesus
    -0.06
     tests
    -0.06
     Alt
    -0.06
     också
    -0.06
     astro
    -0.06
    POSITIVE LOGITS
    ';↵
    0.07
     декоратив
    0.06
    >";↵
    0.06
    ()};↵
    0.06
    /ws
    0.06
     elems
    0.06
    역
    0.06
     gerç
    0.06
    _HS
    0.06
    yntaxException
    0.06
    Act Density 0.047%

    No Known Activations