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

    Neuronpedia

    INDEX
    Explanations

    published works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magna
    -0.07
    	engine
    -0.07
     sweets
    -0.07
    apor
    -0.06
    .br
    -0.06
     робот
    -0.06
    ello
    -0.06
    cedure
    -0.06
    igy
    -0.06
     Pyongyang
    -0.06
    POSITIVE LOGITS
     creditor
    0.06
     Incredible
    0.06
     {})
    0.06
    -start
    0.06
    	animation
    0.06
     coinc
    0.06
    \Form
    0.06
    :utf
    0.06
    _ptr
    0.06
     sid
    0.06
    Act Density 0.046%

    No Known Activations