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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीटर
    -0.07
    ै↵
    -0.07
    ("{}
    -0.07
    دارة
    -0.07
    /Create
    -0.07
    ский
    -0.07
     landfill
    -0.07
    ({});↵
    -0.07
     Impress
    -0.07
     QLabel
    -0.06
    POSITIVE LOGITS
     reconstructed
    0.07
     bats
    0.06
    bursement
    0.05
    (getClass
    0.05
     nationality
    0.05
    bio
    0.05
    ded
    0.05
    never
    0.05
     rozh
    0.05
    stories
    0.05
    Act Density 0.000%

    No Known Activations