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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (newValue
    -0.07
    _arrays
    -0.07
    +W
    -0.07
     đời
    -0.07
    Unified
    -0.06
     hallmark
    -0.06
    #SBATCH
    -0.06
     mai
    -0.06
    ойчив
    -0.06
     Pratt
    -0.06
    POSITIVE LOGITS
    зи
    0.06
    ensely
    0.06
    .sessions
    0.06
     directional
    0.06
     eventdata
    0.06
     Stick
    0.06
    ibur
    0.06
    StatusLabel
    0.06
    egration
    0.06
     Rope
    0.06
    Act Density 0.025%

    No Known Activations