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

    Neuronpedia

    INDEX
    Explanations

    phen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瓜
    -0.06
    arently
    -0.06
     привы
    -0.06
     チ
    -0.06
    ophile
    -0.06
    ěstí
    -0.06
    Pear
    -0.06
    Cerrar
    -0.06
     도
    -0.06
     usernames
    -0.06
    POSITIVE LOGITS
    FLICT
    0.07
     흔
    0.07
    ».
    0.06
     فر
    0.06
     staffing
    0.06
     slice
    0.06
    139
    0.06
     group
    0.06
     (~
    0.06
    	ps
    0.06
    Act Density 0.003%

    No Known Activations