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

    Neuronpedia

    INDEX
    Explanations

    Interpret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     te
    -0.07
     tamp
    -0.07
    rid
    -0.07
    den
    -0.07
    Interesting
    -0.07
    .prof
    -0.07
     Find
    -0.06
    꽤
    -0.06
    (instruction
    -0.06
    Je
    -0.06
    POSITIVE LOGITS
     preferable
    0.08
    _glyph
    0.07
     enums
    0.07
    /use
    0.07
    🦶
    0.07
    pager
    0.07
    	flex
    0.07
     תורה
    0.07
    重型
    0.07
    ervlet
    0.07
    Act Density 0.029%

    No Known Activations