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

    Neuronpedia

    INDEX
    Explanations

    Code/configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     permit
    -0.07
    ):
↵
↵
    -0.07
    нося
    -0.07
    his
    -0.07
    :
↵
↵
    -0.07
     $("#"
    -0.06
    انس
    -0.06
     �
    -0.06
     Taco
    -0.06
    	ll
    -0.06
    POSITIVE LOGITS
    Ups
    0.06
     Spell
    0.06
    _show
    0.06
    ervatives
    0.06
    Reason
    0.06
     Extension
    0.06
    -established
    0.06
     Estimated
    0.06
    _Action
    0.06
    ุข
    0.06
    Act Density 0.024%

    No Known Activations