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

    Neuronpedia

    INDEX
    Explanations

    Scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ix
    -0.06
     нап
    -0.06
     Woo
    -0.06
     Cleans
    -0.06
     handc
    -0.06
     frightened
    -0.06
    ยน
    -0.06
    }`}↵
    -0.06
    _oc
    -0.06
    ?>'
    -0.05
    POSITIVE LOGITS
     defaultdict
    0.07
     بايد
    0.07
     الدول
    0.06
    acente
    0.06
     spared
    0.06
    的に
    0.06
    ,size
    0.06
    κυ
    0.06
    ので
    0.06
     clickable
    0.06
    Act Density 0.024%

    No Known Activations