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

    Neuronpedia

    INDEX
    Explanations

    technology related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KE
    -0.07
    LE
    -0.07
    ango
    -0.07
    ing
    -0.06
     conferences
    -0.06
     objectively
    -0.06
    کل
    -0.06
    كل
    -0.06
    oblin
    -0.06
    ви
    -0.06
    POSITIVE LOGITS
     unseren
    0.07
     },{
    0.07
     uphill
    0.07
     cryptographic
    0.06
     bào
    0.06
    hawks
    0.06
    (reg
    0.06
     pož
    0.06
     motto
    0.06
    zzarella
    0.06
    Act Density 0.258%

    No Known Activations