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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     launch
    -0.08
    ｨ
    -0.07
    ột
    -0.07
    итесь
    -0.07
     beneath
    -0.07
     inaugural
    -0.07
    elsif
    -0.07
    atches
    -0.07
     האינטרנט
    -0.06
    פעולות
    -0.06
    POSITIVE LOGITS
    שג
    0.08
     Boss
    0.08
    羟
    0.07
    +B
    0.07
    (LED
    0.07
    reg
    0.07
     eius
    0.07
    盛行
    0.07
    熬夜
    0.07
    欧元
    0.07
    Act Density 0.091%

    No Known Activations