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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kolej
    -0.06
     znam
    -0.06
    .Qual
    -0.06
    day
    -0.06
    THING
    -0.05
    asje
    -0.05
    UDP
    -0.05
    ircon
    -0.05
    QUIT
    -0.05
    ]){
↵
    -0.05
    POSITIVE LOGITS
    wie
    0.07
    346
    0.07
    eterminate
    0.07
    :'',
    0.07
     feat
    0.06
    urable
    0.06
    321
    0.06
     cane
    0.06
     जबक
    0.06
    cribing
    0.06
    Act Density 0.000%

    No Known Activations