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

    Neuronpedia

    INDEX
    Explanations

    While

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ляется
    -0.07
     aggression
    -0.07
    	username
    -0.07
     src
    -0.07
    Collapse
    -0.07
     فرآ
    -0.06
     originate
    -0.06
     terrorism
    -0.06
     rule
    -0.06
    _cr
    -0.06
    POSITIVE LOGITS
     While
    0.09
    While
    0.07
     Whilst
    0.07
    .While
    0.07
    "While
    0.07
     ncols
    0.07
    Whilst
    0.06
    alarında
    0.06
     MySqlCommand
    0.06
    너
    0.06
    Act Density 0.030%

    No Known Activations