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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.60
    PerformLayout
    -0.54
    RegressionTest
    -0.49
     dealing
    -0.49
     wanting
    -0.47
     enjoying
    -0.47
     helping
    -0.47
     looking
    -0.47
     picking
    -0.46
     spilling
    -0.46
    POSITIVE LOGITS
    穌
    0.60
    Hentet
    0.59
     majestic
    0.58
     Sovereign
    0.56
     AttributeSet
    0.56
    ńskich
    0.55
     hasilnya
    0.54
     käytet
    0.54
    DEP
    0.54
    tellt
    0.53
    Act Density 0.001%

    No Known Activations