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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olia
    -0.07
     Cooper
    -0.07
     Mein
    -0.06
    .account
    -0.06
    ullivan
    -0.06
     shift
    -0.06
    topic
    -0.06
    ’hui
    -0.06
     Highland
    -0.06
     implant
    -0.06
    POSITIVE LOGITS
     blí
    0.07
    inine
    0.07
    umlu
    0.06
    /column
    0.06
     opr
    0.06
    νοι
    0.06
     тов
    0.06
    정이
    0.06
     تص
    0.06
     золот
    0.06
    Act Density 0.016%

    No Known Activations