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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liches
    -0.30
    piring
    -0.30
    è¡·
    -0.27
    è¹ĩ
    -0.26
    mor
    -0.26
    ilton
    -0.25
    åĪ¤
    -0.25
    xin
    -0.24
    RYPT
    -0.24
     meas
    -0.24
    POSITIVE LOGITS
    Facade
    0.29
    åĮħ袱
    0.26
     comp
    0.26
     Clement
    0.26
     bitten
    0.25
    InitialState
    0.24
     Fac
    0.24
    Editing
    0.24
    ãģĬå¾Ĺ
    0.24
    éľĩ
    0.23
    Act Density 0.096%

    No Known Activations