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

    Neuronpedia

    INDEX
    Explanations

    orthogonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automation
    -0.09
     AUG
    -0.09
    xffffffff
    -0.09
    (alert
    -0.08
    automation
    -0.08
     veterans
    -0.08
    run
    -0.07
     антибиот
    -0.07
    Automation
    -0.07
    Aug
    -0.07
    POSITIVE LOGITS
    -circle
    0.09
     onto
    0.09
     برخ
    0.08
     sideways
    0.08
     صلاة
    0.08
     perpendicular
    0.08
     北
    0.08
     Merr
    0.08
     backside
    0.08
     ronda
    0.07
    Act Density 0.003%

    No Known Activations