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

    Neuronpedia

    INDEX
    Explanations

    Social media technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    battle
    -0.08
    .PREFERRED
    -0.08
    氧
    -0.07
    Ax
    -0.07
    good
    -0.06
    god
    -0.06
    "When
    -0.06
    відом
    -0.06
     rok
    -0.06
    /H
    -0.06
    POSITIVE LOGITS
     Sudoku
    0.07
     Migration
    0.07
    umlu
    0.06
     сент
    0.06
     Restore
    0.06
    .ShouldBe
    0.06
     надання
    0.06
     міст
    0.06
     saline
    0.06
     delve
    0.06
    Act Density 0.048%

    No Known Activations