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

    Neuronpedia

    INDEX
    Explanations

    ATP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Poss
    -0.06
    overlay
    -0.06
    .hw
    -0.06
    DropDown
    -0.06
    аду
    -0.06
    (buffer
    -0.06
    ん
    -0.06
    луж
    -0.05
     letto
    -0.05
    �
    -0.05
    POSITIVE LOGITS
    =format
    0.07
    	inst
    0.07
     format
    0.07
     vfs
    0.06
    -wheel
    0.06
     swingers
    0.06
     Consult
    0.06
     disconnect
    0.06
    Wind
    0.06
     Contin
    0.06
    Act Density 0.006%

    No Known Activations