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

    Neuronpedia

    INDEX
    Explanations

    Bell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    그래
    -0.07
    acie
    -0.07
     �
    -0.07
     代
    -0.06
     考
    -0.06
     �
    -0.06
     Tory
    -0.06
     mindset
    -0.06
     ine
    -0.06
    類
    -0.06
    POSITIVE LOGITS
     Bell
    0.22
     bell
    0.20
    Bell
    0.18
    bell
    0.14
     bells
    0.12
     Bella
    0.10
     Belle
    0.09
     belle
    0.09
     Brun
    0.09
    abella
    0.09
    Act Density 0.008%

    No Known Activations