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

    Neuronpedia

    INDEX
    Explanations

    variable references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    覺
    -0.07
    ована
    -0.07
    銷
    -0.07
    Elim
    -0.06
    -----------↵↵
    -0.06
    旦
    -0.06
    ails
    -0.06
    	Message
    -0.06
     NavParams
    -0.06
    _it
    -0.06
    POSITIVE LOGITS
     Θ
    0.07
     bon
    0.07
    ′
    0.06
    (mysql
    0.06
     out
    0.06
     incarcerated
    0.06
     userAgent
    0.06
    UITableView
    0.06
     banged
    0.06
     stint
    0.06
    Act Density 0.029%

    No Known Activations