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

    Neuronpedia

    INDEX
    Explanations

    say "v" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barriers
    -0.07
    index
    -0.07
    [j
    -0.07
    	Action
    -0.07
     Teknik
    -0.06
     barrier
    -0.06
    [type
    -0.06
     TextView
    -0.06
     pyl
    -0.06
    ไทย
    -0.06
    POSITIVE LOGITS
     /**↵
    0.07
     "*.
    0.06
    уда
    0.06
    illac
    0.06
     kterého
    0.06
    до
    0.06
    ilim
    0.06
    zo
    0.06
     이는
    0.06
     JO
    0.06
    Act Density 0.011%

    No Known Activations