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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strs
    -0.07
     konusunda
    -0.07
     Hak
    -0.06
    *self
    -0.06
    -bar
    -0.06
     Bruno
    -0.06
     Rah
    -0.06
    _DISPATCH
    -0.06
    ])/
    -0.06
     Mou
    -0.06
    POSITIVE LOGITS
    شهر
    0.08
     name
    0.07
    uggestions
    0.07
    σταση
    0.07
    _criteria
    0.07
    urb
    0.07
    :CGRectMake
    0.06
    (by
    0.06
    (ll
    0.06
     names
    0.06
    Act Density 0.032%

    No Known Activations