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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aracılığıyla
    -0.07
     Compound
    -0.07
    ウィ
    -0.06
    baş
    -0.06
    erk
    -0.06
     wf
    -0.06
    Road
    -0.06
     teamwork
    -0.06
     дела
    -0.06
    *sin
    -0.06
    POSITIVE LOGITS
    735
    0.06
    _unused
    0.06
          
    0.06
     persever
    0.06
    ++↵
    0.06
    vection
    0.06
    852
    0.06
     Benjamin
    0.06
    	typ
    0.06
    eson
    0.06
    Act Density 0.000%

    No Known Activations