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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    πού
    -0.07
    spender
    -0.07
     currentPage
    -0.07
     आए
    -0.07
    ([('
    -0.06
     WITH
    -0.06
    .includes
    -0.06
    言わ
    -0.06
     singly
    -0.06
    스토
    -0.06
    POSITIVE LOGITS
     blocking
    0.07
     slash
    0.07
     scri
    0.07
     vers
    0.07
     Tom
    0.06
    Slash
    0.06
    Sugar
    0.06
    Tom
    0.06
    	intent
    0.06
    lems
    0.06
    Act Density 0.036%

    No Known Activations