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

    Neuronpedia

    INDEX
    Explanations

    Mars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diary
    -0.07
    /xml
    -0.06
     بیشتری
    -0.06
    année
    -0.06
    708
    -0.06
    IndexOf
    -0.06
     stockings
    -0.06
    moil
    -0.06
    ウォ
    -0.06
    Oil
    -0.06
    POSITIVE LOGITS
     insisted
    0.08
    /Instruction
    0.07
     zemi
    0.07
     Medieval
    0.07
    чил
    0.07
    外
    0.07
     """
↵
↵
    0.07
    (priv
    0.06
     jistě
    0.06
     europe
    0.06
    Act Density 0.008%

    No Known Activations