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

    Neuronpedia

    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	lbl
    -0.07
     Sağlık
    -0.06
    our
    -0.06
     ngắn
    -0.06
     Recover
    -0.06
     Usually
    -0.06
     statutes
    -0.06
     Turk
    -0.06
    “So
    -0.06
     Contractor
    -0.06
    POSITIVE LOGITS
    -Oct
    0.07
     kb
    0.06
     assault
    0.06
    oglobin
    0.06
    .ant
    0.06
    リカ
    0.06
     cruising
    0.06
    -term
    0.06
    ्रव
    0.06
    .*(
    0.06
    Act Density 0.030%

    No Known Activations