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

    Neuronpedia

    INDEX
    Explanations

    tor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cmp
    -0.07
    hard
    -0.07
    -deals
    -0.07
     first
    -0.06
    šil
    -0.06
    альному
    -0.06
    ographies
    -0.06
     işaret
    -0.06
    chein
    -0.06
    aria
    -0.05
    POSITIVE LOGITS
     dak
    0.08
     shift
    0.07
    ạnh
    0.06
     ته
    0.06
     ){
    0.06
    bond
    0.06
     βο
    0.06
    	audio
    0.06
     Yankee
    0.06
    .Agent
    0.06
    Act Density 0.004%

    No Known Activations