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

    Neuronpedia

    INDEX
    Explanations

    data:image/encoded strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arma
    0.50
    haften
    0.49
     Uma
    0.48
     싫
    0.47
    cwnd
    0.46
     Фурга
    0.46
    ’).
    0.44
    et
    0.44
     Ş
    0.44
    ប្រស
    0.44
    POSITIVE LOGITS
    ;
    0.54
     watercolor
    0.52
     europea
    0.52
     canteen
    0.52
     ተጨማሪ
    0.52
    炯
    0.52
     verification
    0.50
    {
    0.50
    জিওথের
    0.50
    ركة
    0.49
    Act Density 0.001%

    No Known Activations