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

    Neuronpedia

    INDEX
    Explanations

    need help with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Config
    0.41
     beurre
    0.36
     Monuments
    0.36
     IMEI
    0.36
     Notes
    0.36
     tours
    0.36
     stairs
    0.35
     hoses
    0.35
     kiles
    0.35
     railings
    0.35
    POSITIVE LOGITS
    fname
    0.36
    ур
    0.36
     достой
    0.34
    insen
    0.33
    rik
    0.33
    conc
    0.33
     нашего
    0.33
    polarity
    0.33
    iat
    0.31
    ortal
    0.31
    Act Density 0.001%

    No Known Activations