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

    Neuronpedia

    INDEX
    Explanations

    numbers between 190 and 230

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
     nim
    -0.08
     secular
    -0.08
    槽
    -0.08
    축
    -0.07
    .jvm
    -0.07
    �
    -0.07
    /constants
    -0.07
    accordion
    -0.07
     Ist
    -0.07
    POSITIVE LOGITS
     William
    0.08
    ांस
    0.08
    ী
    0.08
    ీక
    0.08
    Yeah
    0.07
     ам
    0.07
    (fp
    0.07
    William
    0.07
    \.
    0.07
     �
    0.07
    Act Density 0.237%

    No Known Activations