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

    Neuronpedia

    INDEX
    Explanations

    brackets and braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Masters
    -0.07
     moral
    -0.06
    きな
    -0.06
     Clare
    -0.06
     woo
    -0.06
    �
    -0.06
     neglected
    -0.06
    _FONT
    -0.06
     plausible
    -0.06
     blok
    -0.06
    POSITIVE LOGITS
     Ви
    0.07
    bursement
    0.06
     glove
    0.06
     onUpdate
    0.06
    َج
    0.06
    “As
    0.06
     end
    0.06
    (Number
    0.06
     kW
    0.06
    "As
    0.06
    Act Density 0.052%

    No Known Activations