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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     performer
    -0.06
    eld
    -0.06
     Obr
    -0.06
     cz
    -0.06
     realms
    -0.06
    =self
    -0.06
    WRITE
    -0.06
     numb
    -0.06
     styles
    -0.06
    mob
    -0.06
    POSITIVE LOGITS
     стор
    0.07
    Detect
    0.07
     salad
    0.06
    	s
    0.06
     tack
    0.06
    dete
    0.06
    омина
    0.06
    주의
    0.06
    .CONFIG
    0.06
    appable
    0.06
    Act Density 0.078%

    No Known Activations