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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pounding
    -0.08
     panic
    -0.06
    br
    -0.06
     dific
    -0.06
    ListOf
    -0.06
    Lic
    -0.06
    	str
    -0.06
     bullet
    -0.06
    JR
    -0.06
    ятия
    -0.06
    POSITIVE LOGITS
     OO
    0.06
      ↵
    0.06
    oine
    0.06
     damping
    0.06
    ουν
    0.06
     karşısında
    0.06
    068
    0.06
     "-";↵
    0.06
     Guinea
    0.06
    EQUAL
    0.06
    Act Density 0.033%

    No Known Activations