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

    Neuronpedia

    INDEX
    Explanations

    characters in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    are
    -0.06
    ERVED
    -0.06
     اهد
    -0.06
     xấu
    -0.06
    资料
    -0.06
     δο
    -0.06
     Whatsapp
    -0.06
     elements
    -0.06
    Berry
    -0.06
    (pd
    -0.05
    POSITIVE LOGITS
     settlement
    0.07
     till
    0.07
    amam
    0.07
     settlements
    0.06
    VERTISEMENT
    0.06
     commencement
    0.06
     Trace
    0.06
     proclamation
    0.06
     traitement
    0.06
    σμός
    0.06
    Act Density 0.044%

    No Known Activations