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

    Neuronpedia

    INDEX
    Explanations

    defining terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    default
    -0.07
     NB
    -0.06
     kW
    -0.06
    ोष
    -0.06
    ILA
    -0.06
    iliated
    -0.06
     Cooke
    -0.06
    ICC
    -0.06
     وقتی
    -0.06
    ゥ
    -0.06
    POSITIVE LOGITS
    QRSTUV
    0.08
     prove
    0.07
    Connections
    0.07
     bulunuyor
    0.07
     pObj
    0.06
    %.↵↵
    0.06
     faded
    0.06
     creations
    0.06
    ::::::::::::::
    0.06
    ΙΑΣ
    0.06
    Act Density 0.106%

    No Known Activations