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

    Neuronpedia

    INDEX
    Explanations

    monitoring and effectiveness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dere
    -0.07
    bearing
    -0.07
     em
    -0.06
     반
    -0.06
     второй
    -0.06
    .MON
    -0.06
    頓
    -0.06
     روسی
    -0.06
     RAT
    -0.06
     quatre
    -0.06
    POSITIVE LOGITS
    тив
    0.08
    %%%%
    0.06
    refer
    0.06
    ssue
    0.06
    cheap
    0.06
    .website
    0.06
    ايل
    0.06
     defaultMessage
    0.06
    _align
    0.06
     SOLD
    0.06
    Act Density 0.088%

    No Known Activations