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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Logic
    -0.07
    invest
    -0.07
     Tos
    -0.07
     dictate
    -0.07
    known
    -0.06
    (Student
    -0.06
     tavsiye
    -0.06
    _note
    -0.06
    _STATUS
    -0.06
    Metadata
    -0.06
    POSITIVE LOGITS
    弋
    0.07
     group
    0.07
    	
↵	
↵
    0.07
    modifiers
    0.07
    引用频次
    0.07
    ısının
    0.07
     pornofilm
    0.06
    無しさん
    0.06
    _pcm
    0.06
    :"",↵
    0.06
    Act Density 0.023%

    No Known Activations