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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pag
    -0.07
     ima
    -0.06
     cant
    -0.06
        
    -0.06
            
    -0.06
    illi
    -0.06
    Number
    -0.06
    Mark
    -0.06
     interests
    -0.06
     hobby
    -0.06
    POSITIVE LOGITS
    96
    0.10
    320
    0.08
    128
    0.07
    16
    0.07
    512
    0.07
    288
    0.07
    �
    0.07
    echo
    0.07
     důsled
    0.07
    deep
    0.07
    Act Density 0.204%

    No Known Activations