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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazard
    -0.07
     mechanical
    -0.07
     incident
    -0.07
    .authService
    -0.07
    обще
    -0.07
    Serializable
    -0.07
    	while
    -0.06
     discrete
    -0.06
    rale
    -0.06
     rhyth
    -0.06
    POSITIVE LOGITS
     top
    0.14
    Top
    0.13
     Top
    0.12
    top
    0.12
    (top
    0.11
    	top
    0.11
    _top
    0.11
     TOP
    0.11
    -top
    0.11
    TOP
    0.10
    Act Density 0.039%

    No Known Activations