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

    Neuronpedia

    INDEX
    Explanations

    Identifying facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fronts
    -0.29
    WARE
    -0.27
    wers
    -0.26
    rips
    -0.25
    ån
    -0.25
    ạch
    -0.25
     synonym
    -0.24
    foreground
    -0.24
    emann
    -0.24
     bevor
    -0.24
    POSITIVE LOGITS
    羣çĪ±
    0.26
    OrNull
    0.26
    ä¸ĭä¸Ģ
    0.24
    ç½Ħ
    0.24
    Edited
    0.24
    ·»
    0.24
     mistake
    0.24
    _hid
    0.24
    IService
    0.24
    ëªĩ
    0.24
    Act Density 0.025%

    No Known Activations