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

    Neuronpedia

    INDEX
    Explanations

    coding errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vom
    -0.07
     mem
    -0.07
    Name
    -0.07
     newName
    -0.07
     Provided
    -0.06
    깸
    -0.06
     coastal
    -0.06
     threaten
    -0.06
    Setup
    -0.06
     Presidential
    -0.06
    POSITIVE LOGITS
     sleeves
    0.07
    (open
    0.07
    务
    0.07
    	group
    0.07
    gran
    0.06
    (equal
    0.06
     noodles
    0.06
     duplicates
    0.06
    aktu
    0.06
    _('
    0.06
    Act Density 0.094%

    No Known Activations