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
     fora
    -0.07
     financ
    -0.07
     проз
    -0.07
    aş
    -0.07
     학교
    -0.07
    [event
    -0.06
     несколь
    -0.06
    �
    -0.06
     Barg
    -0.06
     біль
    -0.06
    POSITIVE LOGITS
     RIGHT
    0.07
     Yellowstone
    0.06
    NOW
    0.06
    <Expression
    0.06
    ùi
    0.06
    need
    0.06
    ','"+
    0.05
     Right
    0.05
    qualified
    0.05
    ieder
    0.05
    Act Density 0.007%

    No Known Activations