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

    Neuronpedia

    INDEX
    Explanations

    echo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Blueprint
    -0.07
     moth
    -0.07
    结束
    -0.07
    질
    -0.06
     relocated
    -0.06
     Weapon
    -0.06
     seinem
    -0.06
    opa
    -0.06
     tram
    -0.06
    ład
    -0.06
    POSITIVE LOGITS
    fts
    0.07
    ็
    0.07
    ję
    0.06
    ƒ
    0.06
     expectations
    0.06
    MOTE
    0.06
     handwritten
    0.06
     Falling
    0.06
     boots
    0.06
     Lite
    0.06
    Act Density 0.004%

    No Known Activations