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

    Neuronpedia

    INDEX
    Explanations

    narratives of distress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oplan
    -0.06
     reassuring
    -0.06
    -confirm
    -0.06
    	tp
    -0.06
    ENCIL
    -0.06
    simulation
    -0.06
     Equality
    -0.06
     acqu
    -0.06
     publishers
    -0.06
    ,Object
    -0.06
    POSITIVE LOGITS
     {{--<
    0.07
     Sinatra
    0.06
     [+
    0.06
    .Views
    0.06
     نگهد
    0.06
    unsqueeze
    0.06
    ー�
    0.06
     fyz
    0.06
    ，不
    0.06
    DOCKER
    0.06
    Act Density 0.047%

    No Known Activations