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

    Neuronpedia

    INDEX
    Explanations

    important notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.57
     (>
    0.44
     {
    0.42
     ((
    0.40
     (~
    0.39
     If
    0.38
     ¿
    0.38
     Dacă
    0.37
     )
    0.37
     (“
    0.36
    POSITIVE LOGITS
    Cordial
    0.45
    Kya
    0.41
    ों
    0.41
    Karma
    0.40
    いますが
    0.40
    zeniach
    0.40
     있지만
    0.39
    하지만
    0.39
    ława
    0.39
    Meesho
    0.38
    Act Density 0.186%

    No Known Activations