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

    Neuronpedia

    INDEX
    Explanations

    manage these, for both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ণী
    0.43
    Mesh
    0.39
    Quest
    0.39
    anlagen
    0.38
    ostat
    0.38
    Conta
    0.38
     flip
    0.37
    mez
    0.37
    ethers
    0.37
     سلي
    0.36
    POSITIVE LOGITS
    ಿದ್ದೇವೆ
    0.40
    ম্বে
    0.39
     preserve
    0.39
     देशमुख
    0.39
     आंतरिक
    0.38
    ENIDO
    0.38
     invariance
    0.38
     muted
    0.38
     збере
    0.38
     זו
    0.38
    Act Density 0.000%

    No Known Activations