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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Choi
    -0.08
    CID
    -0.07
    	protected
    -0.07
    !
↵
    -0.07
    (filename
    -0.07
    _OUTPUT
    -0.07
     PHP
    -0.06
    (objects
    -0.06
    (ro
    -0.06
    agnostic
    -0.06
    POSITIVE LOGITS
     бел
    0.07
     handing
    0.07
    aven
    0.06
     represents
    0.06
     masturbating
    0.06
    ände
    0.06
    headed
    0.06
    ừng
    0.06
     expires
    0.06
    Parsing
    0.06
    Act Density 0.008%

    No Known Activations