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

    Neuronpedia

    INDEX
    Explanations

    local

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stitution
    -0.07
    .FromSeconds
    -0.06
    	parse
    -0.06
     ermög
    -0.06
     Sell
    -0.06
     Meredith
    -0.06
    -ins
    -0.06
    _View
    -0.06
    Radius
    -0.06
     buffering
    -0.06
    POSITIVE LOGITS
     للأ
    0.07
     vật
    0.07
    을
    0.07
    �
    0.06
     أخرى
    0.06
     Toxic
    0.06
    481
    0.06
    _SWITCH
    0.06
    @s
    0.06
     subordinate
    0.06
    Act Density 0.007%

    No Known Activations