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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DATA
    -0.08
    �
    -0.07
    .par
    -0.07
    .guard
    -0.06
     Kant
    -0.06
     thái
    -0.06
    	filter
    -0.06
    ότε
    -0.06
     formations
    -0.06
    .return
    -0.06
    POSITIVE LOGITS
    mj
    0.07
    скому
    0.06
     blister
    0.06
    :'',
    0.06
    ptest
    0.06
     Conor
    0.06
    OTOS
    0.06
    (btn
    0.06
     eff
    0.06
    coach
    0.06
    Act Density 0.045%

    No Known Activations