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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ана
    -0.08
    else
    -0.07
     forth
    -0.07
    Ber
    -0.06
     feasibility
    -0.06
    надлеж
    -0.06
     Также
    -0.06
     fatigue
    -0.06
    	pp
    -0.06
    	test
    -0.06
    POSITIVE LOGITS
    _DRV
    0.07
     Tide
    0.06
    ichever
    0.06
    clf
    0.06
     widgets
    0.06
     člán
    0.06
    Organization
    0.06
    663
    0.06
     vocab
    0.06
     Gerry
    0.06
    Act Density 0.051%

    No Known Activations