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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .about
    -0.08
    orWhere
    -0.07
    .restore
    -0.07
    StartTime
    -0.06
     部
    -0.06
    는데
    -0.06
     äl
    -0.06
     wieder
    -0.06
     EXTI
    -0.06
    .orm
    -0.06
    POSITIVE LOGITS
    acea
    0.08
    sport
    0.07
     exhausting
    0.07
     YORK
    0.06
    views
    0.06
     Libyan
    0.06
    ��
    0.06
     molds
    0.06
    omit
    0.06
     markdown
    0.06
    Act Density 0.001%

    No Known Activations