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

    Neuronpedia

    INDEX
    Explanations

    rhetorical comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    .Toast
    -0.06
    중
    -0.06
     predecessors
    -0.06
     stomach
    -0.06
     Sark
    -0.06
    isSelected
    -0.06
    married
    -0.06
    민
    -0.06
    /cgi
    -0.06
    POSITIVE LOGITS
    dere
    0.07
     бать
    0.06
     количество
    0.06
    (company
    0.06
     auf
    0.06
     음
    0.06
     इतन
    0.06
     patched
    0.06
     десят
    0.06
     afirm
    0.06
    Act Density 0.046%

    No Known Activations