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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts globally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lans
    0.44
    átiles
    0.44
    ើស
    0.43
    ঞ্চল্য
    0.41
     untenable
    0.41
    ამე
    0.41
     murderous
    0.40
    CEPTION
    0.40
     depositions
    0.40
    AMOS
    0.40
    POSITIVE LOGITS
     roar
    0.44
    ↵
    0.44
    正是
    0.42
     form
    0.41
     Dim
    0.41
     Verify
    0.40
     һәм
    0.40
     العلماء
    0.39
     ര
    0.39
     and
    0.39
    Act Density 0.000%

    No Known Activations