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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ึง
    -0.07
    PX
    -0.07
     ژانویه
    -0.06
    _yaw
    -0.06
    	sig
    -0.06
     sequ
    -0.06
     hrs
    -0.06
    Highlighted
    -0.06
     populous
    -0.06
    chts
    -0.06
    POSITIVE LOGITS
     strikes
    0.07
    �
    0.06
    ON
    0.06
     killing
    0.06
     inflicted
    0.06
     operational
    0.06
    ाव
    0.06
    zee
    0.06
    non
    0.06
     Mack
    0.06
    Act Density 0.115%

    No Known Activations