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

    Neuronpedia

    INDEX
    Explanations

    widely available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Err
    0.41
     Verne
    0.40
     Er
    0.39
     Эр
    0.38
     Err
    0.38
    GBuf
    0.37
    ச்சின்ன
    0.36
    ӓ
    0.36
    䒑
    0.35
    Shore
    0.34
    POSITIVE LOGITS
    Cris
    0.44
     Cris
    0.41
    페
    0.38
    cris
    0.36
    CM
    0.35
    φέ
    0.34
    James
    0.34
     cris
    0.33
    餸
    0.33
     primer
    0.33
    Act Density 0.011%

    No Known Activations