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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (the
    -0.08
     interactions
    -0.07
     albums
    -0.07
     risks
    -0.07
     reboot
    -0.07
     interacting
    -0.07
     nightly
    -0.07
    getCurrent
    -0.07
    GN
    -0.06
     Kho
    -0.06
    POSITIVE LOGITS
    Unc
    0.07
    Apollo
    0.06
     التح
    0.06
     giriş
    0.06
    "};↵↵
    0.06
    upos
    0.06
    ってる
    0.05
     grpc
    0.05
     empleado
    0.05
    	results
    0.05
    Act Density 0.198%

    No Known Activations