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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fa
    -0.07
     detach
    -0.07
     нали
    -0.07
    SBATCH
    -0.07
     данных
    -0.06
     REQ
    -0.06
    鸟
    -0.06
     deterrent
    -0.06
    (spell
    -0.06
    ntl
    -0.06
    POSITIVE LOGITS
    (x
    0.09
    =X
    0.08
    _X
    0.08
     examined
    0.07
     examine
    0.07
    =x
    0.07
    X
    0.07
     XIII
    0.07
    xmin
    0.07
    {x
    0.07
    Act Density 0.093%

    No Known Activations