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

    Neuronpedia

    INDEX
    Explanations

    phase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kant
    -0.07
     stripped
    -0.07
     Lisp
    -0.07
     Diocese
    -0.07
     Kudos
    -0.07
    Desk
    -0.07
     Rack
    -0.07
    ush
    -0.07
     IService
    -0.07
    son
    -0.07
    POSITIVE LOGITS
     отход
    0.09
     проход
    0.08
    nti
    0.08
     жили
    0.08
    ilate
    0.08
     العالية
    0.08
    walking
    0.08
     сустав
    0.08
     പുല
    0.08
     alternating
    0.08
    Act Density 0.003%

    No Known Activations