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

    Neuronpedia

    INDEX
    Explanations

    lo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nested
    -0.07
    �
    -0.06
    άνα
    -0.06
    afari
    -0.06
     beta
    -0.06
    acr
    -0.06
     الإسلام
    -0.06
    agt
    -0.06
     uomini
    -0.06
    olute
    -0.06
    POSITIVE LOGITS
     Dominican
    0.07
    _LVL
    0.07
    (file
    0.06
     δημο
    0.06
     logfile
    0.06
    طه
    0.06
    blo
    0.06
     condo
    0.06
     prem
    0.06
     permissible
    0.06
    Act Density 0.000%

    No Known Activations