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

    Neuronpedia

    INDEX
    Explanations

    what or the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LIABILITY
    -0.07
     Employee
    -0.07
    dup
    -0.07
    Observer
    -0.07
    ॉल
    -0.07
     irony
    -0.07
    uccess
    -0.06
    ()],↵
    -0.06
    addListener
    -0.06
     gelişim
    -0.06
    POSITIVE LOGITS
     accommodating
    0.06
     vant
    0.06
     psy
    0.06
     defeats
    0.06
     mean
    0.06
     primer
    0.06
     เม
    0.06
     syn
    0.06
    �
    0.06
     win
    0.06
    Act Density 0.008%

    No Known Activations