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

    Neuronpedia

    INDEX
    Explanations

    Both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tÃł
    -0.30
    .cl
    -0.30
    à¸ĺา
    -0.27
    Certificate
    -0.25
     Certificate
    -0.24
    (acc
    -0.24
    Recipient
    -0.24
    ippers
    -0.24
     certificate
    -0.24
     din
    -0.23
    POSITIVE LOGITS
    urbation
    0.30
    uron
    0.27
    çļĦåŃ¦ä¹ł
    0.26
    è¾ħ导
    0.26
    æĸ°åĬłåĿ¡
    0.26
    ãĥ¶
    0.25
    -saving
    0.25
     зн
    0.24
    mind
    0.24
    unt
    0.23
    Act Density 0.494%

    No Known Activations