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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ια
    -0.07
     ponds
    -0.07
     Depot
    -0.07
    الك
    -0.07
     الثاني
    -0.07
     patrol
    -0.07
    klady
    -0.07
    .ali
    -0.06
     encoder
    -0.06
    リア
    -0.06
    POSITIVE LOGITS
    を見
    0.06
     keyCode
    0.06
    илання
    0.06
    	perror
    0.06
    urum
    0.06
    [curr
    0.06
    _holder
    0.06
     صنعت
    0.06
     aktiv
    0.06
     engages
    0.05
    Act Density 0.021%

    No Known Activations