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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negotiate
    -0.07
    Los
    -0.07
    holders
    -0.07
     union
    -0.07
     malware
    -0.07
    WR
    -0.07
    (dataset
    -0.07
    谈
    -0.06
     chart
    -0.06
     arousal
    -0.06
    POSITIVE LOGITS
    usunda
    0.06
    ِه
    0.06
    (xx
    0.06
    )o
    0.06
    (update
    0.06
     unlimited
    0.06
    IntoConstraints
    0.06
     *)((
    0.06
     "-
    0.06
    (exit
    0.06
    Act Density 0.015%

    No Known Activations