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

    Neuronpedia

    INDEX
    Explanations

    interpret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Proc
    -0.07
     descarga
    -0.07
    irable
    -0.07
     Cla
    -0.07
     Catalogue
    -0.07
    용
    -0.07
     확보
    -0.07
    -0.07
     ensam
    -0.07
    Classpath
    -0.07
    POSITIVE LOGITS
     interpreting
    0.10
     أننا
    0.10
     interpretar
    0.10
     interpreted
    0.09
     creatively
    0.09
     interpre
    0.09
     intenção
    0.09
     parts
    0.09
     твор
    0.09
     interpretation
    0.08
    Act Density 0.029%
    No Known Activations