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

    Neuronpedia

    INDEX
    Explanations

    escape key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ${
    0.56
     gratuit
    0.54
     detached
    0.54
     käyt
    0.54
    ad
    0.51
    able
    0.50
    im
    0.49
     из
    0.49
    ,
    0.49
     cl
    0.49
    POSITIVE LOGITS
    휙
    0.58
     Soon
    0.56
    वरिश
    0.55
    Ꮡ
    0.55
    0.50
    ፫
    0.50
    ᔾ
    0.49
    𝙵
    0.48
    ♰
    0.48
    خم
    0.47
    Act Density 0.000%

    No Known Activations