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

    Neuronpedia

    INDEX
    Explanations

    Scarves and ties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tax
    -0.09
    �
    -0.07
     Tax
    -0.07
    accine
    -0.07
    יא
    -0.07
    患
    -0.07
    残留
    -0.07
    萧
    -0.07
    伐
    -0.07
    رأ
    -0.07
    POSITIVE LOGITS
    还包括
    0.08
    เฉ
    0.07
     afirm
    0.07
     initializing
    0.07
    editable
    0.06
    .Debugf
    0.06
     finishes
    0.06
    (disposing
    0.06
     enables
    0.06
     Soft
    0.06
    Act Density 0.009%

    No Known Activations