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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    थ
    -0.07
    ена
    -0.07
     intros
    -0.06
    ipt
    -0.06
     tvá
    -0.06
    י�
    -0.06
    ён
    -0.06
    Presence
    -0.06
     hé
    -0.06
     τά
    -0.06
    POSITIVE LOGITS
    Benef
    0.07
     hour
    0.07
    crets
    0.06
    TimeString
    0.06
    Metadata
    0.06
    Prosec
    0.06
    +'_
    0.06
    arsed
    0.06
    Otherwise
    0.06
    Detailed
    0.06
    Act Density 0.156%

    No Known Activations