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

    Neuronpedia

    INDEX
    Explanations

    IR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pregn
    -0.06
     навч
    -0.06
     dopo
    -0.06
    contro
    -0.06
    lád
    -0.06
     kills
    -0.06
     определен
    -0.06
     debtor
    -0.06
     uomo
    -0.06
    =search
    -0.06
    POSITIVE LOGITS
    ayout
    0.08
     вод
    0.06
    .Fat
    0.06
    LN
    0.06
     formally
    0.06
    su
    0.06
    ZIP
    0.06
     limitations
    0.06
     MQ
    0.06
    	const
    0.06
    Act Density 0.005%

    No Known Activations