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

    Neuronpedia

    INDEX
    Explanations

    radio/public broadcasting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clothing
    -0.07
     detailed
    -0.07
    Rights
    -0.07
    Disabled
    -0.07
     WA
    -0.07
     newObj
    -0.06
    Canadian
    -0.06
     climate
    -0.06
    政治
    -0.06
     будів
    -0.06
    POSITIVE LOGITS
    801
    0.07
     vign
    0.06
    try
    0.06
    式会社
    0.06
     freel
    0.06
     것도
    0.06
    iện
    0.05
    。それ
    0.05
    xde
    0.05
    =g
    0.05
    Act Density 0.022%

    No Known Activations