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

    Neuronpedia

    INDEX
    Explanations

    physics equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HIGH
    -0.07
     Javier
    -0.07
    工
    -0.07
    няют
    -0.06
    уму
    -0.06
    _pool
    -0.06
    	new
    -0.06
     spaces
    -0.06
    \Validator
    -0.06
    239
    -0.06
    POSITIVE LOGITS
     Europeans
    0.07
    quivos
    0.06
    maxlength
    0.06
     userDao
    0.06
    (PARAM
    0.06
     Haziran
    0.06
     taj
    0.06
     جشن
    0.06
    환경
    0.06
     böl
    0.06
    Act Density 0.017%

    No Known Activations