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

    Neuronpedia

    INDEX
    Explanations

    Networking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     две
    -0.07
    _wf
    -0.07
     ceremony
    -0.07
    〜
    -0.07
     klu
    -0.07
    ERG
    -0.07
     Có
    -0.07
     mujer
    -0.07
    oteca
    -0.06
     hac
    -0.06
    POSITIVE LOGITS
     �
    0.06
    getPosition
    0.06
    	of
    0.06
     金
    0.06
     getWindow
    0.06
    errors
    0.05
    .SUCCESS
    0.05
     __________________________________
    0.05
    £o
    0.05
    Lazy
    0.05
    Act Density 0.025%

    No Known Activations