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

    Neuronpedia

    INDEX
    Explanations

    admissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entries
    -0.07
     went
    -0.07
    олж
    -0.06
     library
    -0.06
    _alpha
    -0.06
     �
    -0.06
    	headers
    -0.06
    상담
    -0.06
    piece
    -0.06
     Bert
    -0.06
    POSITIVE LOGITS
    ROLE
    0.07
    buyer
    0.07
    three
    0.06
    "',↵
    0.06
    NSMutableArray
    0.06
    ,List
    0.06
     discovery
    0.06
    prung
    0.06
    (load
    0.06
     shoots
    0.06
    Act Density 0.001%

    No Known Activations