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

    Neuronpedia

    INDEX
    Explanations

    stainless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Trans
    -0.07
     bus
    -0.06
    Pref
    -0.06
    	iter
    -0.06
    	conf
    -0.06
     chancellor
    -0.06
    ero
    -0.06
     chip
    -0.06
     Agu
    -0.06
     Bullet
    -0.06
    POSITIVE LOGITS
     permutations
    0.06
    irement
    0.06
    之前
    0.06
     utilisateur
    0.06
     Stainless
    0.06
    vidence
    0.06
     SETTINGS
    0.06
     indirectly
    0.06
    consin
    0.06
     докум
    0.06
    Act Density 0.002%

    No Known Activations