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

    Neuronpedia

    INDEX
    Explanations

    clear edges or leading zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     देम
    0.43
     sadistic
    0.43
     anguish
    0.42
     unimagin
    0.41
    แต่ละ
    0.41
    ༣
    0.41
     wretched
    0.40
     betrayal
    0.40
    惘
    0.39
    ༠
    0.39
    POSITIVE LOGITS
     (
    0.47
    /
    0.41
    9
    0.41
    -
    0.40
    7
    0.39
     “
    0.39
          
    0.39
     Memorial
    0.37
    8
    0.37
     Vitamin
    0.36
    Act Density 0.372%

    No Known Activations