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

    Neuronpedia

    INDEX
    Explanations

    /or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dice
    -0.07
    /send
    -0.06
    หร
    -0.06
    rado
    -0.06
     �
    -0.06
     Spare
    -0.06
     кв
    -0.06
    _quote
    -0.06
     "*"
    -0.06
    .chain
    -0.06
    POSITIVE LOGITS
    Someone
    0.07
    empl
    0.07
    	cv
    0.07
    erman
    0.06
     reported
    0.06
     Lars
    0.06
    림
    0.06
    029
    0.06
     hook
    0.06
    REFER
    0.06
    Act Density 0.002%

    No Known Activations