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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subclasses
    -0.07
     issued
    -0.07
    -------------
    -0.07
    --------
    -0.07
     convict
    -0.07
    Gs
    -0.06
    Ben
    -0.06
    -St
    -0.06
    	onChange
    -0.06
    -0.06
    POSITIVE LOGITS
    neh
    0.07
    lap
    0.06
     जब
    0.06
    _PCIE
    0.06
     kazanç
    0.06
     پاسخ
    0.06
    ekce
    0.06
    ektör
    0.06
     Prism
    0.06
    าม
    0.06
    Act Density 0.004%

    No Known Activations