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

    Neuronpedia

    INDEX
    Explanations

    verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insuffisamment
    0.42
    צות
    0.39
     maneuver
    0.38
     ovarian
    0.38
     manoeuvre
    0.38
    ার্ড
    0.37
    quetas
    0.37
    Scroll
    0.37
    ্যন্তরীণ
    0.35
     idios
    0.35
    POSITIVE LOGITS
     verification
    1.39
     Verification
    1.38
     verify
    1.35
     verifies
    1.35
     verifying
    1.34
    验证
    1.27
     Verify
    1.27
    Verification
    1.24
    verification
    1.24
    verify
    1.23
    Act Density 0.036%

    No Known Activations