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

    Neuronpedia

    INDEX
    Explanations

    decide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visto
    -0.07
     на
    -0.06
     Gh
    -0.06
    473
    -0.06
     magnificent
    -0.06
     불
    -0.06
     흔
    -0.06
     Libraries
    -0.06
     milf
    -0.06
    phant
    -0.06
    POSITIVE LOGITS
    *))
    0.07
    (confirm
    0.07
    _LOADING
    0.06
    eguard
    0.06
     крови
    0.06
     CORE
    0.06
    Binder
    0.06
    ферен
    0.06
    onec
    0.06
    0.06
    Act Density 0.006%

    No Known Activations