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

    Neuronpedia

    INDEX
    Explanations

    Strange character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     po
    -0.07
    126
    -0.07
     upro
    -0.07
    129
    -0.06
    	LP
    -0.06
    (car
    -0.06
    378
    -0.06
     zost
    -0.06
     jeszcze
    -0.06
    71
    -0.06
    POSITIVE LOGITS
    0.08
    ../../../
    0.07
     SCI
    0.07
    ?><?
    0.07
    ancements
    0.07
    ОН
    0.07
    /todo
    0.07
    .addElement
    0.06
     лишь
    0.06
    ी
    0.06
    Act Density 0.011%

    No Known Activations