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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Record
    -0.07
    нож
    -0.07
     liter
    -0.07
     incoming
    -0.07
    lash
    -0.06
    _clr
    -0.06
    Week
    -0.06
    comed
    -0.06
    ¸
    -0.06
    MBER
    -0.06
    POSITIVE LOGITS
     construct
    0.06
     constructing
    0.06
     příro
    0.06
    طب
    0.06
     appare
    0.06
    ('').
    0.06
    (Constants
    0.05
     técn
    0.05
     Lastly
    0.05
    .getCmp
    0.05
    Act Density 0.000%

    No Known Activations