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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Macro
    -0.07
    _shop
    -0.06
     Creature
    -0.06
    кового
    -0.06
     swims
    -0.06
    ród
    -0.06
    Ingredient
    -0.06
    $name
    -0.06
    $user
    -0.06
    _GATE
    -0.06
    POSITIVE LOGITS
    acyj
    0.07
     Jud
    0.06
    Toolbar
    0.06
     notify
    0.06
     advisers
    0.06
    bakan
    0.06
    减
    0.06
     JO
    0.06
     Complex
    0.06
     SCIP
    0.06
    Act Density 0.011%

    No Known Activations