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

    Neuronpedia

    INDEX
    Explanations

    Code generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andr
    -0.07
     phrase
    -0.06
    	point
    -0.06
    _em
    -0.06
     pr
    -0.06
    ;


↵
    -0.06
    	post
    -0.06
    éf
    -0.06
    \uc
    -0.06
     scenarios
    -0.06
    POSITIVE LOGITS
    ์ของ
    0.07
     giải
    0.07
     शर
    0.06
    ोर
    0.06
     Newport
    0.06
    .pageY
    0.06
    Liverpool
    0.06
    его
    0.06
     Hutch
    0.06
    Thor
    0.06
    Act Density 0.001%

    No Known Activations