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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maternity
    -0.08
    omal
    -0.08
     monthly
    -0.07
    \Extension
    -0.06
     awful
    -0.06
    Bow
    -0.06
    птом
    -0.06
    andest
    -0.06
     sprawling
    -0.06
     Erl
    -0.06
    POSITIVE LOGITS
    {
    0.07
    จะได
    0.07
    （昭和
    0.06
     человека
    0.06
    ávky
    0.06
     jong
    0.06
    据
    0.06
    仅
    0.06
    <Q
    0.06
     Air
    0.06
    Act Density 0.020%

    No Known Activations