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

    Neuronpedia

    INDEX
    Explanations

    Professional work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hdc
    -0.07
     δια
    -0.06
    uw
    -0.06
    urse
    -0.06
    Lu
    -0.06
    usual
    -0.06
    ينية
    -0.06
     účast
    -0.06
    Lik
    -0.06
    ΑΛ
    -0.06
    POSITIVE LOGITS
     Expand
    0.07
    (TreeNode
    0.07
    .’
    0.06
     Deleted
    0.06
    aled
    0.06
    AtPath
    0.06
     Chronicles
    0.06
    PASS
    0.06
     imagining
    0.06
    ¤¤
    0.06
    Act Density 0.039%

    No Known Activations