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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .redirect
    -0.07
    _notification
    -0.07
     bak
    -0.06
    oram
    -0.06
    strncmp
    -0.06
    	player
    -0.06
    ーニ
    -0.06
    �
    -0.06
    idenav
    -0.06
    883
    -0.06
    POSITIVE LOGITS
    Letter
    0.08
     bigotry
    0.07
    elist
    0.07
    ph
    0.07
    /disable
    0.07
     utrecht
    0.07
     PR
    0.07
    (Char
    0.07
     wall
    0.07
    )
↵
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations