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

    Neuronpedia

    INDEX
    Explanations

    LOSS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vir
    -0.07
    HDR
    -0.06
    frica
    -0.06
    _MSG
    -0.06
     weird
    -0.06
    .chunk
    -0.06
    _checks
    -0.06
    बर
    -0.06
    вед
    -0.06
    	dialog
    -0.06
    POSITIVE LOGITS
     lack
    0.08
    _distribution
    0.07
     basket
    0.07
    -package
    0.07
    duct
    0.06
     disappeared
    0.06
     LOSS
    0.06
     losses
    0.06
    ект
    0.06
     ул
    0.06
    Act Density 0.002%

    No Known Activations