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

    Neuronpedia

    INDEX
    Explanations

    basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lower
    -0.08
    -reset
    -0.07
     "*"
    -0.07
     explore
    -0.07
     paper
    -0.07
     '#'
    -0.06
    pers
    -0.06
    como
    -0.06
    Initialized
    -0.06
    NullPointerException
    -0.06
    POSITIVE LOGITS
     basic
    0.08
     bằng
    0.06
     sama
    0.06
    افية
    0.06
     stump
    0.06
     counterfeit
    0.06
    siyon
    0.06
    ό
    0.06
     pimp
    0.06
     GÜ
    0.06
    Act Density 0.011%

    No Known Activations