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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ratio
    -0.08
     Tour
    -0.07
     expressions
    -0.07
    Service
    -0.07
    -around
    -0.07
    Sessions
    -0.06
    .restart
    -0.06
    	inter
    -0.06
     lesson
    -0.06
     shear
    -0.06
    POSITIVE LOGITS
     prostoru
    0.07
     insurgency
    0.06
     इतन
    0.06
    لسل
    0.06
    ]];
    0.06
    Gu
    0.06
     tục
    0.06
    ┐
    0.06
     kuş
    0.06
    ligt
    0.06
    Act Density 0.008%

    No Known Activations