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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Px
    -0.07
    ازل
    -0.06
     thuốc
    -0.06
    _cipher
    -0.06
    _write
    -0.06
    cap
    -0.06
    _Store
    -0.06
    受到
    -0.06
    pants
    -0.06
    Fields
    -0.06
    POSITIVE LOGITS
    笑
    0.07
    -describedby
    0.07
     ALLOW
    0.06
     draining
    0.06
     upgrades
    0.06
     uncovered
    0.06
     заверш
    0.06
    ญ
    0.06
     нав
    0.06
    lluminate
    0.06
    Act Density 0.015%

    No Known Activations