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

    Neuronpedia

    INDEX
    Explanations

    visual inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brake
    0.40
     Synopsis
    0.39
     Break
    0.39
     Clare
    0.38
     Carole
    0.38
     Go
    0.37
     GO
    0.37
    entine
    0.36
     Stages
    0.35
     Guatemala
    0.35
    POSITIVE LOGITS
     giardino
    0.45
    妑
    0.41
    شمند
    0.40
     abundantly
    0.40
    قیع
    0.40
    संर
    0.39
    քում
    0.38
    ំន
    0.38
    мили
    0.38
     филосо
    0.38
    Act Density 0.000%

    No Known Activations